Merge branch 'f-138-fixB' into f-138-prs

A rebinding page cannot send the key, so with one configured the check only
broke tunnels and proxies that pass their own name on (cloudflared does).
Keyless setups keep it, with allowed_hosts; the 403 now also says that
setting an API key turns the check off.

.dockerignore

@@ -0,0 +1,27 @@
+# Keep the image to the source only: everything generated is re-created on
+# first start (inside the container or on the /data volume).
+.git
+
+# local Python environment (rebuilt in the image)
+.venv/
+__pycache__/
+*.pyc
+.pytest_cache/
+
+# setup.py outputs and downloads (engine, packs, models, logs)
+/engine/
+/build/
+/build*/
+/dist/
+/packs/
+/mtp/
+/models/
+/Strata-data/
+third_party/llama.cpp/
+third_party/*.zip
+*.done
+*.log
+strata-*.json
+strata-*.txt
+run-*.sh
+run-*.bat

.gitattributes

@@ -4,3 +4,6 @@ bench/prompts/** -text
 # launchers keep their platform line endings wherever the repository is cloned
 *.sh text eol=lf
 *.bat text eol=crlf
+
+# copies of real packs' native_experts.txt, parsed byte for byte by tests/core/expert_layout_test.cpp
+tests/data/native_experts/** -text

.github/FUNDING.yml

@@ -0,0 +1 @@
+buy_me_a_coffee: strataengine

.gitignore

@@ -18,6 +18,8 @@ __pycache__/
 
 # plan v0.3 P1 (repository hygiene, review E1): profiler captures and large diagnostic dumps stay out of git.
 *.nsys-rep
+
+# Pi harness metadata (local session state, not project source)
 *.sqlite
 *.npz
 *.occ1
@@ -26,7 +28,7 @@ td.log
 # created by setup.py on the user's machine
 /.venv/
 /build/
-/third_party/llama.cpp/
+/third_party/llama.cpp
 /models/
 /packs/
 /mtp/
@@ -35,6 +37,7 @@ td.log
 /strata-*.json
 /strata-*.log
 /build-strata.bat
+/.strata-mcp/
 
 # image encoder (setup.py --vision): build output and the generated build script
 build-vision*/
@@ -47,3 +50,4 @@ build-vision.bat
 *.done
 /third_party/*.zip
 
+/.rocm-win/

AGENTS.md

@@ -0,0 +1,23 @@
+# AGENTS.md
+
+Strata runs the Qwen3.8-Flash-Next mixture-of-experts model (and its Coder, Swift 1.5 and Unsloth variants) on a
+normal PC: one NVIDIA or AMD graphics card plus system RAM, on Windows or Linux. It has a C++/CUDA/HIP engine
+(`src/`, `include/`), a Python server with an OpenAI- and Anthropic-compatible API and a web app (`serve/`), and a
+one-click installer (`setup.py`, started by `START-HERE.bat` / `setup.sh`).
+
+## Installing Strata for a user
+
+Follow **[docs/AI_SETUP.md](docs/AI_SETUP.md)**: check the PC, pick the model by RAM, run setup non-interactively,
+start and verify the server, and connect the user's apps. Never expose the server beyond `127.0.0.1` without
+`--api-key`. As an alternative to shell commands, Strata's MCP server ([docs/MCP_SERVER.md](docs/MCP_SERVER.md))
+offers the same steps as tools.
+
+## Working on the code
+
+- How the engine works, every measured number, the API and all settings: [docs/DETAILS.md](docs/DETAILS.md) and
+  the [paper](docs/paper/Strata-Paper.pdf).
+- AMD (HIP) build and validation: [docs/AMD_HIP.md](docs/AMD_HIP.md); multi-GPU: [docs/MULTI_GPU.md](docs/MULTI_GPU.md).
+- Setup's own tests run without a GPU or downloads: `python tools/test_setup_<name>.py` (for example
+  `tools/test_setup_amd.py`, `tools/test_setup_choices.py`).
+- Keep the docs' style: plain words, measured numbers with what they were measured on, no claims without a
+  measurement.

Dockerfile

@@ -0,0 +1,115 @@
+# syntax=docker/dockerfile:1
+#
+# Strata: Qwen3.8-Flash-Next on NVIDIA GPUs (RTX 30/40/50, 12+ GB VRAM; two or
+# three cards can share one model, 8 GB each - docs/MULTI_GPU.md).
+#
+# The engine is compiled during docker build, so the first container start only
+# downloads the model (~70 GB) and starts the server. docker build has no GPU,
+# so the CUDA architectures are fixed here instead of read from nvidia-smi: the
+# engine is a fat binary with a cubin per listed arch, and the runtime picks the
+# one matching your card. Narrow CUDA_ARCHITECTURES to your card for a faster
+# build; a card outside the set needs a rebuild with its own arch.
+#
+# Build:
+#   docker build -t strata .
+#   docker build -t strata --build-arg CUDA_ARCHITECTURES=89 .        # RTX 40 only
+#
+# Run (host needs an NVIDIA driver >= 580 and nvidia-container-toolkit):
+#   docker run --rm --gpus all \
+#     -p 8080:8080 \
+#     --ulimit memlock=-1 \
+#     -v strata-data:/data \
+#     -e MODEL=IQ2_XS \
+#     strata
+#
+# Setup choices are env vars, read by docker-entrypoint.sh: FAMILY, MODEL, CONTEXT,
+# VISION (no | yes | cpu), KV (int8 | q4_0 | k8v4), GPU (one card) or GPUS ("0,2"
+# or "all", with LAYER_SPLIT), LOW_RAM (auto | on | off), HOST, PORT, API_KEY.
+#
+# Only the model files, the prepared pack, the MTP layer and the install config
+# live in the /data volume; the engine is part of the image. Strata loads 32-62 GB
+# into RAM, so a capped container needs -e LOW_RAM=on: setup.py reads the RAM from
+# /proc/meminfo, which here is the host's total, not the container's limit. Add an
+# API key before exposing the port to a network: -e API_KEY=<secret>. Pass
+# -e REINSTALL=1 to change the model settings later.
+#
+# --gpus all on a host with two usable cards: setup takes both (the layer split is
+# its recommended default). Pin one card with -e GPU=0, or name them with
+# -e GPUS=0,2. A volume set up for one card switches to the pair on its first start
+# on a two-card host unless GPU or GPUS pins it. LOW_RAM=on runs on one card.
+
+FROM nvidia/cuda:13.0.0-devel-ubuntu24.04
+
+# STRATA_EXECV=1: setup.py replaces itself with the server, so the server is PID 1
+# and docker stop's SIGTERM reaches it (see setup.start). Normal Linux starts, which
+# don't set it, keep spawning the server as a child.
+ENV DEBIAN_FRONTEND=noninteractive PYTHONUNBUFFERED=1 LANG=C.UTF-8 STRATA_EXECV=1
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        build-essential ca-certificates curl git libatomic1 libgomp1 \
+        python3 python3-pip python3-venv unzip \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /opt/strata
+COPY . .
+
+# RTX 20 (75), RTX 30 (86), RTX 40 (89), RTX 50 (120), plus 80 for A-series. CMakeLists
+# refuses anything below 75. BUILD_VISION=0 skips the image encoder build.
+ARG CUDA_ARCHITECTURES=75;80;86;89;120
+ARG BUILD_VISION=1
+
+RUN python3 -m venv .venv \
+    && .venv/bin/pip install --no-cache-dir --upgrade pip \
+    && .venv/bin/pip install --no-cache-dir -r requirements.txt \
+    && chmod +x setup.sh docker-entrypoint.sh
+
+# llama.cpp at the pinned commit, then the engine and the image encoder, built
+# exactly the way setup.py builds them. BUILD.json is what setup.py reads to
+# decide whether an engine is current: source=local with a matching src hash
+# means the first start reuses it instead of recompiling.
+RUN .venv/bin/python - <<'PYEOF'
+import json, os, pathlib, shutil
+import setup
+
+llama = setup.get_llama_cpp()
+nvcc, _ = setup.find_nvcc()
+arch = os.environ.get("CUDA_ARCHITECTURES", "75;80;86;89;120").strip().strip('"').replace(",", ";")
+vision = "gpu" if os.environ.get("BUILD_VISION", "1") == "1" else "none"
+
+setup.cmake_build(setup.ROOT, setup.ROOT / "build", "strata",
+    ["-DSTRATA_ENABLE_CUDA=ON", "-DSTRATA_BUILD_TESTS=OFF",
+     f"-DCMAKE_CUDA_ARCHITECTURES={arch}", f"-DCMAKE_CUDA_COMPILER={nvcc}",
+     f"-DSTRATA_GGML_DIR={llama}"], None, "build-strata.bat")
+if vision != "none":
+    setup.cmake_build(setup.ROOT / "tools" / "vision", setup.ROOT / "build-vision", "strata-vision",
+        [f"-DLLAMA_DIR={llama}", "-DSTRATA_VISION_CUDA=ON",
+         f"-DCMAKE_CUDA_ARCHITECTURES={arch}", f"-DCMAKE_CUDA_COMPILER={nvcc}"], None, "build-vision.bat")
+
+eng = setup.ROOT / "engine"
+eng.mkdir(exist_ok=True)
+shutil.copy2(setup.ROOT / "build" / setup.EXE, eng / setup.EXE)
+if vision != "none":
+    shutil.copy2(setup.ROOT / "build-vision" / "bin" / setup.VEXE, eng / setup.VEXE)
+bindir = pathlib.Path(nvcc).parent
+meta = {"source": "local", "version": setup.source_version(),
+        "archs": [int(a.split("-")[0]) for a in arch.split(";") if a.split("-")[0].isdigit()], "vision": vision,
+        "cuda_dirs": [str(d) for d in (bindir, bindir / "x64", bindir.parent / "lib64") if d.is_dir()],
+        "src": setup.source_hash(setup.ENGINE_SOURCES),
+        "vision_src": setup.source_hash(setup.VISION_SOURCES) if vision != "none" else None}
+(eng / "BUILD.json").write_text(json.dumps(meta, indent=1))
+PYEOF
+
+# the cmake trees are build-time only; the engine itself is what the container needs
+RUN rm -rf build build-vision
+
+VOLUME ["/data"]
+EXPOSE 8080
+
+# /health is answered before the API key gate, so it works with or without one.
+# The port only opens after the model loads (1-3 minutes, longer on a first run),
+# so the start period is generous: a too short one marks a still-loading container
+# unhealthy and a restart policy would kill it mid-download.
+HEALTHCHECK --interval=30s --timeout=5s --start-period=600s --retries=3 \
+  CMD curl -fs "http://127.0.0.1:${PORT:-8080}/health" || exit 1
+
+ENTRYPOINT ["./docker-entrypoint.sh"]

README.md

@@ -1,206 +1,185 @@
 <h1 align="center">Strata</h1>
 
-<p align="center"><b>Run a 125-billion-parameter AI model on a normal gaming PC</b><br>
-one NVIDIA card (12-24 GB) + 64 GB of RAM · Windows or Linux · one click to install</p>
+<p align="center"><b>Run a 125-billion-parameter AI model on your own gaming PC</b><br>
+NVIDIA or AMD graphics card (12 GB or more) · Windows or Linux · free and open source</p>
 
 <p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="A voxel pagoda garden that Strata's model wrote, running in the browser"></a><br>
 <sub>A voxel pagoda garden, 1 shot prompt running on an RTX 5070 with Strata (IQ3_S, 128K context) ·
 <a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4">full video (49 s)</a></sub></p>
 
 Strata runs **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)** - a large, smart AI model that
-normally needs a server - on your own PC. It writes its answers at **60-95 tokens per second** (a token is about ¾
-of a word): faster than you can read.
-
-- **Free and open source.**
-
-> **Jump to:** [How fast?](#how-fast-is-it) · [Which model?](#which-model-should-i-pick) · [Install](#install) ·
-> [Using it](#using-it) · [Problems?](#something-went-wrong) · [How it works](#how-does-it-work) ·
-> [All the details](docs/DETAILS.md)
-
----
+normally needs a server - on a normal PC. It chats, writes code, reads pictures and works with your apps and coding
+agents, and nothing leaves your PC.
 
 ## How fast is it?
 
-Measured on an RTX 5070 (12 GB), a Ryzen 5 7600 and 64 GB of RAM:
+Measured on two ordinary gaming PCs. "Writes answers" is how fast the reply appears in a short chat; "reads your
+prompt" is how fast it takes in what you send (a 32K-token document, code or chat history). A token is about ¾ of a
+word, so 60 tokens per second is faster than you can read.
 
-| Size | Writes answers (short chat) | Writes answers (128K context) | Reads your prompt |
-| --- | ---: | ---: | ---: |
-| **Q2_0** | 90 tokens/s | 67 tokens/s | 1,310 tokens/s |
-| **IQ2_XS** | 74 tokens/s | 60 tokens/s | 1,240 tokens/s |
-| **IQ3_XXS** | 62 tokens/s | 46 tokens/s | 1,110 tokens/s |
-| **IQ3_S** | 52 tokens/s | 41 tokens/s | 1,070 tokens/s |
-| **Coder** (IQ1_M) | 51 tokens/s | 44 tokens/s | 1,300 tokens/s |
+<table>
+<tr><th>NVIDIA: RTX 5070 (12 GB), Ryzen 5 7600, 64 GB RAM</th><th>AMD: RX 9070 XT (16 GB), Ryzen 9 3900X, 47 GB RAM</th></tr>
+<tr><td>
 
-- **Writes answers** = how fast the reply appears (tokens per second).
-- **Reads your prompt** = how fast it takes in what you send (long documents, code, chat history), measured on a
-  32K-token prompt; a 4K prompt reads at 740-1,000 tokens/s. A 32K prompt takes about 25 seconds with Q2_0.
+| Size | Writes answers | Reads your prompt |
+| --- | ---: | ---: |
+| **Q2_0** | 94 tokens/s | 2,650 tokens/s |
+| **IQ2_XS** | 79 tokens/s | 2,090 tokens/s |
+| **IQ3_XXS** | 62 tokens/s | 1,750 tokens/s |
+| **IQ3_S** | 53 tokens/s | 1,620 tokens/s |
+| **Coder** | 55 tokens/s | 2,180 tokens/s |
 
-A card with more VRAM is faster, because more of the model fits on the GPU: an RTX 3090 (24 GB) should do roughly
-100-140 tokens per second. All measurements, long-context numbers and estimates for other cards are in the
-[details](docs/DETAILS.md#speed-measured).
+</td><td>
 
-Every PC is different: `START-HERE.bat --calibrate` measures a few engine settings on yours and keeps the fastest
-(about 5-10 minutes; on the PC above it made the Coder 7% faster).
+| Size | Writes answers | Reads your prompt |
+| --- | ---: | ---: |
+| **Q2_0** | 60 tokens/s | 1,160 tokens/s |
+| **IQ2_XS** | 52 tokens/s | 1,110 tokens/s |
+| **Coder** | 44 tokens/s | 1,420 tokens/s |
 
-## Which model should I pick?
+</td></tr>
+</table>
 
-**The size** (the same model, compressed more or less):
+A card with more VRAM is faster: an RTX 3090 (24 GB) should write roughly 100-140 tokens per second. Long chats,
+other cards: [speed of each model](docs/MODELS.md#how-fast-is-each-size), [community results](docs/COMMUNITY_BENCHMARKS.md).
 
-| Model | RAM+VRAM Requirements | Speed | Quality |
-| --- | ---: | --- | --- |
-| **Q2_0** | 37.6 GB | fastest | good |
-| **IQ2_XS** | 39.2 GB | fast | better (**recommended**) |
-| **IQ3_XXS** | 47.0 GB | slower | great |
-| **IQ3_S** | 54.8 GB | slowest | best: matches the full model on the published tests (original model only) |
+<p align="center"><a href="https://buymeacoffee.com/strataengine"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" height="50"></a><br>
+<sub>Strata is free. If it runs well on your PC, a coffee keeps the work on it going.</sub></p>
 
-**Will it fit?** Shard 1 is the part of the model that gets loaded when it starts: its experts go into your **RAM**,
-the rest onto your graphics card (the second shard, a 29 GB lookup table, stays on the SSD). So it fits when your
-**RAM is at least shard 1 + about 10 GB** for Windows and your other programs. With 64 GB of RAM every size fits
-(IQ3_S with little else open); with 48 GB, Q2_0 and IQ2_XS. A bigger graphics card makes it faster, but it doesn't
-lower the RAM needed.
+## What you need
 
-**The version:**
+| | |
+| --- | --- |
+| **Graphics card** | **NVIDIA** GeForce RTX 20, 30, 40 or 50 series, or **AMD** Radeon RX 7900 XT / XTX, RX 7800 XT / 7700 XT, RX 9060 XT, RX 9070 / 9070 XT, Radeon AI PRO R9700 or RX 6800 / 6900 series - with **12 GB of VRAM or more** |
+| **RAM** | 32 GB or more - how much decides [which model](#which-model-should-i-pick) fits; 64 GB runs every size |
+| **Disk** | about 80 GB free, on an SSD if you can (the first start is much faster) |
+| **System** | Windows 10 / 11 or Linux, and a current graphics driver from NVIDIA or AMD |
 
-- **Qwen3.8-Flash-Next** - the original.
-- **[Coder](https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF)** - ISTA-DASLab's coding
-  version: half of the experts removed, keeping the ones that code, tool use and images need (91% of the full model's
-  SWE-bench Verified score, 99% of LiveCodeBench, by its authors). One size (IQ1_M: its experts stored like IQ3_S):
-  shard 1 is **29.6 GB**, so it fits a PC with **32 GB of RAM**, runs 262K context on 64 GB, and reads long prompts
-  the fastest of all. Weaker outside coding.
-- **[Swift 1.5](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF)** - a fine-tune by UkisAI
-  that thinks much shorter before answering, so you get the answer sooner, with about the same quality. Same speed per
-  token, and about the same RAM as the same size of the original (no IQ3_S). Its own license applies (see its page).
-
-Not sure? Take **IQ2_XS** - or the **Coder** if you mainly write code, or have 32-48 GB of RAM. You can add another
-one later with `SETUP.bat` (the same as `START-HERE.bat --setup`; on Linux `./setup.sh --setup`).
+Everything else is installed for you. Two or three cards can share the model ([multi-GPU](docs/MULTI_GPU.md)).
+The full list: [docs/INSTALL.md](docs/INSTALL.md#what-you-need).
 
 ## Install
 
-**You need:** an NVIDIA RTX 30, 40 or 50 card with 12 GB of VRAM or more, enough RAM for the size you pick (above),
-~80 GB of free disk space (an SSD makes the first start much faster), and Windows 10/11 or Linux. The only thing you
-install yourself is a current **NVIDIA driver** ([nvidia.com/drivers](https://www.nvidia.com/drivers) or the NVIDIA
-App). Everything else - Python, the engine, the model - is set up for you.
+### Let your AI set it up
 
-**Windows**
+Use an AI coding assistant (Claude Code, Cursor, Codex, GitHub Copilot, ...)? Paste this into it:
 
-1. [Download this project](https://github.com/Niko1221/Strata/archive/refs/heads/main.zip) and unzip it (or `git clone` it).
-2. Double-click **`START-HERE.bat`**.
-3. Answer a few questions - or just press Enter each time for the recommended choice:
-   - **Which model and size?** The original or Swift 1.5, and Q2_0, IQ2_XS, IQ3_XXS or IQ3_S - see [above](#which-model-should-i-pick)
-   - **How much context?** How much text it can keep in mind at once (it suggests one for your card)
-   - **Images?** Whether it should also read pictures
-   - **Experimental speed projection?** Off unless you say yes - [read what it does](docs/DETAILS.md#experimental-speed-projection-experimental-off-by-default) first
+```text
+Set up Strata on this PC for me: https://github.com/Niko1221/Strata - follow docs/AI_SETUP.md in that repository.
+```
 
-Then it downloads everything (the model is ~70 GB, so the first time takes a while - you can stop and it picks up
-where it left off) and **starts the model**. Your browser opens the Strata app at `http://127.0.0.1:8080`.
+It checks your graphics card, RAM and disk, picks the model that fits, installs it, starts it and tells you how to
+connect your apps. AI tools can also install, start and stop Strata themselves through its
+[MCP server](docs/MCP_SERVER.md).
+
+### Or do it yourself
+
+[Download Strata](https://github.com/Niko1221/Strata/archive/refs/heads/main.zip) and unzip it (or `git clone` it).
+**Windows:** double-click **`START-HERE.bat`**. **Linux:** run **`./setup.sh`** in the Strata folder.
+
+The same steps for NVIDIA and AMD: the installer finds your card and sets up the right engine for it. It asks which
+model, which size, how much context (how much text it keeps in mind) and whether it should read pictures - press
+Enter each time for the recommended answer. Then it downloads the model (~70 GB; you can stop and it continues where
+it left off) and starts it. Your browser opens the Strata app at `http://127.0.0.1:8080`.
 
 > **While the model starts, your PC can be slow or stop responding for 1-3 minutes** (longest the first time): Strata
 > loads 35-55 GB into your RAM and locks part of it for the graphics card. That's normal - wait, and don't close the
 > window. The window tells you what it is doing.
 
-**Next time**, just double-click `START-HERE.bat` again: it starts right away, nothing is downloaded twice. Close its
-window to stop the model.
+**Next time**, run `START-HERE.bat` (or `./setup.sh`) again: it starts right away, nothing is downloaded twice. Close
+its window to stop the model. `UPDATE.bat` (`./update.sh`) updates Strata without starting it. Updating, Docker,
+several cards, where the files go and every option:
+[docs/INSTALL.md](docs/INSTALL.md).
 
-**Updating:** download the new version and unzip it anywhere (or `git pull`), then run `START-HERE.bat` in it. The
-model files are kept in a `Strata-data` folder next to your Strata folder, so a new copy finds them and sets itself up
-the same way - nothing big is downloaded again.
+## Which model should I pick?
 
-**Linux:** run `./setup.sh` - same questions, same result.
+The installer recommends one for your RAM. The same model comes in sizes that are compressed more or less: smaller
+is faster, larger is a bit smarter.
+
+| Your RAM | Take | Why |
+| --- | --- | --- |
+| **32 GB** | **Coder** | it fits 32 GB, and it is made for code (with a 24 GB card, Q2_0 and IQ2_XS run too) |
+| **48 GB** | **IQ2_XS** (or Q2_0, the fastest) | the larger sizes do not fit |
+| **64 GB** | **IQ2_XS** (recommended), or IQ3_XXS / IQ3_S | every size fits; IQ3_S is the best, and the slowest |
+| **96 GB or more** | **IQ3_S**, or Unsloth's 4-bit (experimental) | room for the largest sizes with everything else open |
+
+- **[Coder](docs/MODELS.md#coder)** - a coding version with half of the experts removed: 91% of the full model's
+  SWE-bench Verified score (by its authors), fits 32 GB of RAM. Weaker outside code, including Chinese and other
+  CJK text (#438): for those, take Q2_0, IQ2_XS or IQ3_S, which keep every expert.
+- **[Swift 1.5](docs/MODELS.md#swift-15)** - a fine-tune that thinks much shorter before it answers, so you get the
+  answer sooner, at about the same quality.
+- **[Unsloth UD-Q4_K_XL](docs/MODELS.md#unsloth-ud-q4_k_xl-experimental)** (experimental) - the closest to the full
+  model, but most of it is read from the SSD while it answers: 7-8.5 tokens/s on a 64 GB PC.
+- **[OrcaRouter's Uncensored IQ3_XXS](docs/MODELS.md#orcarouter-uncensored-iq3_xxs)** - a manual setup, not in the
+  installer's menu.
+
+Sizes, downloads and what fits where: [docs/MODELS.md](docs/MODELS.md). You can add another model later with
+`SETUP.bat` (Linux: `./setup.sh --setup`).
 
 ## Using it
 
 <p align="center"><img src="docs/media/runpagoda.png" width="900" alt="The Strata app's Monitor tab next to a coding agent"><br>
 <sub>The Strata app's <b>Monitor</b> (left) while a coding agent writes the pagoda garden from the video (right)</sub></p>
 
-- **In the browser:** `http://127.0.0.1:8080` - the Strata app (it opens by itself when the model starts): **Chat**, a
-  live **Monitor** of the model and your GPU/CPU/RAM, and **About** with the settings and addresses.
-- **Chat in the terminal:** `.venv\Scripts\python chat.py`
-- **Your apps and coding agents:** add it as an "OpenAI-compatible" provider with base URL
-  **`http://127.0.0.1:8080/v1`**, any API key and any model name. Apps that use Anthropic's API: `http://127.0.0.1:8080/v1/messages`.
-- **Thinking:** the model thinks before it answers. Choose **off, low, medium or high** - in the chat page menu, with
-  `/think low` in `chat.py`, or with your app's "reasoning effort" setting. Off is fastest; high is best for hard questions.
-- **Pictures:** in the chat page click **Picture**; in `chat.py` type `/image <path>`; in apps just attach them.
-- **From your phone or another PC:** `START-HERE.bat --setup --host 0.0.0.0 --api-key <secret>`, then open the
-  address the server window prints; see the [details](docs/DETAILS.md#using-it).
-- **Experimental speed projection (off by default):** an experimental control vector that setup can turn on; it
-  changes how the model answers - read [what it does](docs/DETAILS.md#experimental-speed-projection-experimental-off-by-default) first.
+- **In the browser:** `http://127.0.0.1:8080` - **Chat**, a live **Monitor** of the model and your GPU/CPU/RAM, and
+  **About** with the settings and addresses.
+- **Your apps and coding agents:** add an "OpenAI-compatible" provider with base URL **`http://127.0.0.1:8080/v1`**,
+  any API key and any model name. Apps that use Anthropic's API: `http://127.0.0.1:8080/v1/messages` (Claude Code:
+  `ANTHROPIC_BASE_URL=http://127.0.0.1:8080`).
+- **Thinking:** choose **off, low, medium or high** in the chat menu or your app's "reasoning effort". Off is
+  fastest; high is best for hard questions.
+- **Pictures:** say yes to "Images?" in setup, then click **Picture** in the chat, or attach them in your app
+  (AMD cards: on Linux through the processor, not on Windows yet).
+- **From your phone or another PC:** `START-HERE.bat --setup --host 0.0.0.0 --api-key <secret>` - always with a key.
+- **Good to know:** it answers one request at a time. The first message of a chat is read in full (about 1 minute
+  per 30,000 tokens); follow-ups start in seconds.
 
-**Good to know:** it answers one request at a time. The first message of a chat is read in full (about 1 minute per
-30,000 tokens); after that it keeps the conversation and reads only what is new, so follow-ups start in seconds.
+More: [where your chats are stored](docs/INSTALL.md#where-things-are-stored), [the API](docs/DETAILS.md#using-it).
 
 ## Something went wrong?
 
-**My PC froze, or got very slow, the first time Strata started.**
-That's normal while it starts, most of all the first time. Strata loads 35-55 GB into your RAM, locks part of it for
-the graphics card, and works out how much of the model fits on your GPU. The mouse can freeze for a few minutes. **Wait, and don't close the
-window.** The next starts are much faster. Still frozen after 10 minutes? Restart the PC, close other programs
-(browsers use a lot of RAM) and try again. If it keeps happening, pick a smaller size (Q2_0 or IQ2_XS).
+- **My PC froze the first time Strata started.** Normal while it loads the model: wait, don't close the window.
+  Still frozen after 10 minutes? Restart the PC, close other programs and try again, or pick a smaller size.
+- **It stopped while downloading or installing.** Run `START-HERE.bat` (or `./setup.sh`) again: it continues where
+  it stopped.
+- **It's very slow and the disk light keeps blinking, or "the engine stopped unexpectedly".** Not enough free RAM:
+  close other programs (browsers use a lot), or pick a smaller size (Q2_0 or IQ2_XS).
+- **It says port 8080 is already in use.** Strata is already running - look for its window.
 
-**It stopped while downloading or installing.**
-Run `START-HERE.bat` again. It continues where it stopped.
-
-**It says the NVIDIA driver is too old.**
-Update it (NVIDIA App or [nvidia.com/drivers](https://www.nvidia.com/drivers)), restart the PC, and run
-`START-HERE.bat` again.
-
-**It says port 8080 is already in use.**
-Strata is already running. Look for its window.
-
-**It's very slow and the disk light keeps blinking.**
-Your PC is out of free RAM. Close other programs, or pick a smaller size (Q2_0 or IQ2_XS).
-
-**An answer stopped with "the engine stopped unexpectedly".**
-Usually not enough RAM (on Linux the system then stops the engine). Just send your message again: Strata starts the
-engine by itself. If it keeps happening, close other programs or pick a smaller size.
-
-**It says the prompt exceeds the context.**
-The conversation is longer than the context you chose. Start a new chat, or run `SETUP.bat` and pick more
-context.
-
-**Still stuck?** Look in the [full troubleshooting table](docs/DETAILS.md#troubleshooting), or open an issue and
-attach `strata-<model>.log` from the Strata folder.
+More problems and their fixes: [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md). Still stuck? Open an
+[issue](https://github.com/Niko1221/Strata/issues) and attach `strata-<model>.log` from the Strata folder.
 
 ## How does it work?
 
 Models like this one normally run on servers with hundreds of gigabytes of graphics memory. Your graphics card has
-12-24 GB. Strata makes it fit by **sharing the work across your whole PC** - the same idea as a kitchen, where the
-things you use all the time stay on the counter and the rest waits in the pantry.
+12-24 GB. Strata makes it fit by **sharing the work across your whole PC** - like a kitchen, where the things you use
+all the time stay on the counter and the rest waits in the pantry.
 
 <p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="The model's 24,576 experts: the busiest on the graphics card, all of them in RAM, a lookup table on the SSD"></p>
 
-- **The model is a team of 24,576 small specialists ("experts"),** and each word it writes needs only 10 of them.
-  So it doesn't have to have all of them on the graphics card at once.
-- **Your graphics card** does the part of the work needed for every word, and keeps the few thousand experts that
-  are asked most often. It keeps learning which ones those are while you use it.
-- **Your RAM** holds every expert. When a word needs one the card doesn't have, **your processor** works on it -
-  at the same time as the graphics card, so neither waits for the other.
-- **Your SSD** holds a big lookup table; the model only reads a few small rows of it per word.
+- **The model is a team of 24,576 small specialists ("experts"),** and each word needs only 10 of them.
+- **Your graphics card** keeps the few thousand experts that are asked most often; **your RAM** holds all of them,
+  and **your processor** works on the rest at the same time. **Your SSD** holds a big lookup table.
 
 <p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="A small helper guesses the next words; the big model checks them all at once and keeps the right ones"></p>
 
-- **Guess, then check.** A small, fast helper built into the model guesses the next few words, and the big model
-  checks all the guesses in one go. It keeps the ones it agrees with and writes the next word itself - so one step
-  often produces several words. The helper only guesses - the big model decides every word - so you get the same
-  quality answer, 1.6-1.8x sooner.
-- **Long texts are read in big pieces** (up to 8,192 tokens - pieces of words - at a time), which is why a long
-  document or code base is read at over 1,000 tokens per second.
+- **Guess, then check:** a small helper guesses the next few words and the big model checks them all at once, so
+  you get the same answer, 1.6-1.8x sooner.
+- **Long texts are read in big pieces** (up to 8,192 tokens at a time): over 1,000 tokens per second.
 
-Want the full picture? The [details](docs/DETAILS.md#how-it-works) explain every part and its numbers, and the
-[paper](docs/paper/Strata-Paper.pdf) tells the whole story, with the measurements behind it.
+The longer explanation: [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md). Every part and its numbers: [the
+details](docs/DETAILS.md#how-it-works) and the [paper](docs/paper/Strata-Paper.pdf).
 
-## Credits
+## Credits and license
 
-- Model: [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) by the Qwen team; compressed versions by
-  [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF);
-  [Swift 1.5](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF) by UkisAI. Their licenses apply
-  to the model files.
-- Built with parts of [llama.cpp / ggml](https://github.com/ggml-org/llama.cpp) (MIT). Ideas from
-  [Splash](https://github.com/incoai/splash), [ninfer](https://github.com/Neroued/ninfer) and
-  [HyperQwen](https://github.com/syv-ai/HyperQwen). More in the [details](docs/DETAILS.md#credits-and-licenses).
+The model is [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) by the Qwen team, compressed by
+[ISTA-DASLab](https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF), UkisAI (Swift 1.5) and Unsloth;
+Strata is built with parts of [llama.cpp / ggml](https://github.com/ggml-org/llama.cpp). All credits:
+[docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits). Strata is open source under the [MIT License](LICENSE); a few
+parts and every model carry their own licenses ([which ones](docs/HOW_IT_WORKS.md#license)).
 
-## License
+## Support Strata
 
-Strata is open source under the [MIT License](LICENSE). A few parts carry their own licenses: `third_party/ggml`
-(MIT, llama.cpp / ggml), the web app's font (SIL Open Font License 1.1) and the experimental speed projection's
-vector in `data/experimental-speed-projection` (Qwen Community License 1.0, from the model's activations). The
-models are not part of this repository; each model's own license applies to its files.
+Strata is free and open source. If it is useful to you, you can support its development:
+
+<p align="center"><a href="https://buymeacoffee.com/strataengine"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" height="50"></a></p>

START-HERE.bat

@@ -1,6 +1,6 @@
 @echo off
 rem Strata for Windows: the first run installs everything and starts the model; later runs just start it.
-rem Needs only an NVIDIA driver. Python is installed for your user account if it is missing (no admin needed).
+rem Needs only an NVIDIA or AMD graphics driver. Python is installed for your user account if it is missing (no admin needed).
 setlocal
 title Strata
 cd /d "%~dp0"

UPDATE.bat

@@ -0,0 +1,36 @@
+@echo off
+rem Update Strata without starting the model (#475): the newest code (git pull, when this folder is a git clone), then
+rem what START-HERE.bat does before a start - the engine (a new one when this version needs it), the Python packages,
+rem each installed model's settings and draft subset. The model files are not touched. Start the model later with
+rem START-HERE.bat. Options are passed on to setup.py.
+setlocal
+title Strata - update
+cd /d "%~dp0"
+rem All of it in one block: cmd reads a .bat file while it runs it, and the git pull can change this very file.
+(
+  if exist ".git" (
+    where git >nul 2>nul || (
+      echo  This folder is a git clone, but git is not on PATH: install Git for Windows ^(winget install Git.Git^)
+      echo  or run "git pull" here yourself, then run UPDATE.bat again.
+      pause
+      exit /b 1
+    )
+    echo  Getting the newest Strata ^(git pull^) ...
+    git pull --ff-only || (
+      echo.
+      echo  git pull did not succeed ^(the reason is above^): nothing was updated. Files you changed here can stop it:
+      echo  "git status" lists them.
+      pause
+      exit /b 1
+    )
+  ) else (
+    echo  This copy of Strata was not made with git, so it cannot fetch new files itself. Download the newest one:
+    echo    https://github.com/Niko1221/Strata/archive/refs/heads/main.zip
+    echo  unzip it anywhere and run START-HERE.bat ^(or UPDATE.bat^) in it: it finds the model files in Strata-data
+    echo  and sets itself up the same way - nothing big is downloaded again.
+    echo  Checking this copy's engine and settings meanwhile ...
+  )
+  call "%~dp0START-HERE.bat" --update %*
+  if not errorlevel 1 pause
+  exit /b
+)

bench/results/2026-09-28-rope-scaling/README.md

@@ -0,0 +1,49 @@
+# Rope scaling: needle recall past the trained 262K
+
+The feature (PR #84, experimental): `--rope-scaling none|linear|yarn` extends the context past the model's
+trained 262,144 positions by rescaling the rotary angles - llama.cpp's types, ggml's `rope_yarn`
+arithmetic, one process config applied at the cos/sin table (default path) and as kernel constants
+(`--native-rope`, the native indexer, prefill). The three tables here are the first end-to-end check
+that a scaled run actually recalls past the trained end.
+
+**Hardware:** RTX 4070 Ti SUPER 16 GB, Ryzen 9 5900X (no AVX-512 - the IQ3_XXS native pack runs its
+expert kernels on AVX-2), 125 GB RAM, Linux. **Engine:** this branch built from source (the log records
+`rope scaling ... --max-context ... against a trained context of 262144` at startup). The runs below
+were taken on the rope tree built over the 0.1.17-era base; the branch then rebased onto main (engine
+0.1.20) - the drift touches none of the rope files - and the rebase was re-validated: `rope_parity`
+green, a 64-token greedy run token-identical to the plain 0.1.20 build, and the yarn 262k probe
+repeated green (see the last table row). Baseline arm A also re-checked the default is the stock
+model: a 64-token greedy run produces the same token ids as the ready-made 0.1.17 engine, and
+`rope_parity` holds the `none` table bit-identical to the pre-scaling builder.
+**Method:** `tools/needle_bench.py` against a running server (launch recipes in `config-*.json`),
+`temperature 0`, thinking off, depth 50%, one probe per length.
+
+| Arm | Scaling | Context | Probe | Prompt tokens | Result | Probe time |
+| --- | --- | --- | --- | --- | --- | --- |
+| A | none | 262,144 | 1k @ 50% | 1,442 | FOUND | 4 s |
+| A | none | 262,144 | 32k @ 50% | 31,763 | FOUND | 27 s |
+| A | none | 262,144 | 128k @ 50% | 128,328 | FOUND | 86 s |
+| B | linear, factor 2 | 560,000 | 262k @ 50% | 274,222 | FOUND | 232 s |
+| B | linear, factor 2 | 560,000 | 512k @ 50% | 527,051 | FOUND | 619 s |
+| C | yarn, factor 2 | 560,000 | 262k @ 50% | 274,215 | FOUND | 236 s |
+| C | yarn, factor 2 | 560,000 | 512k @ 50% | 526,988 | FOUND | 615 s |
+| C | yarn, factor 2 | 560,000 | 262k @ 50% (the rebase re-check) | 273,708 | FOUND | 235 s |
+
+All 8 of 8 probes found the needle; JSON per arm: `needle-A-none.json`, `needle-B-linear2.json`,
+`needle-B-linear2-512k.json`, `needle-C-yarn2.json` (+ the rebase re-check in
+`needle-C-yarn2-rebased.json`); server and engine logs alongside.
+
+What this establishes, and what it does not:
+
+- **Past the trained end the model still reads.** 512k probes are 2.01x the trained 262,144 - position
+  interpolation (B) and YaRN (C) both hold a mid-context lookup there.
+- **Scaled runs within the trained range are a slightly different model.** `yarn`'s mscale applies at
+  every position (a 64-token greedy prompt diverges from the stock run after ~19 tokens); arm A is the
+  stock model, arms B/C are not, by design.
+- **One depth, one needle, one machine.** A single probe per (length, arm) at depth 50% says "recall
+  works there", not "no degradation anywhere" - a full depth sweep and a longer-length ladder (768K,
+  1M) on the bench machine (64 GB RAM there vs 125 GB here, so 262K IQ3_XXS fits either way) is the
+  natural follow-up. 512K prompts prefill at ~850-950 tokens/s on this card; the probe time is almost
+  entirely prefill.
+- **The `560,000` context** in arms B/C is headroom for the needle harness's tokenizer overshoot
+  (a "512k" probe tokenizes to ~527k); 524,288 exactly would refuse the probe.

bench/results/2026-09-28-rope-scaling/config-A-none-262144.json

@@ -0,0 +1,38 @@
+{
+ "exe": "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata/build/strata",
+ "cwd": "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata",
+ "tokenizer": "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/packs/iq3_xxs/tokenizer",
+ "model_name": "qwen3.8-flash-next-iq3_xxs-rope-scaling",
+ "lib_dirs": [
+  "/usr/local/cuda/bin",
+  "/usr/local/cuda/lib64"
+ ],
+ "port": 8130,
+ "args": [
+  "--pack",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/packs/iq3_xxs",
+  "--native",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/models/IQ3_XXS/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00001-of-00002.gguf",
+  "--ple-gguf",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/models/IQ3_XXS/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00002-of-00002.gguf",
+  "--expert-profile",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata/data/expert-profile.bin",
+  "--expert-cache",
+  "auto",
+  "--prefill",
+  "auto",
+  "--spec",
+  "4",
+  "--spec-min-p",
+  "0.5",
+  "--mtp",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/mtp/rt",
+  "--kv",
+  "int8",
+  "--kv-resident",
+  "32768",
+  "--max-context",
+  "262144"
+ ],
+ "log": "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata/bench/results/2026-09-28-rope-scaling/engine-A-none-262144.log"
+}

bench/results/2026-09-28-rope-scaling/config-B-linear2.json

@@ -0,0 +1,42 @@
+{
+ "exe": "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata/build/strata",
+ "cwd": "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata",
+ "tokenizer": "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/packs/iq3_xxs/tokenizer",
+ "model_name": "qwen3.8-flash-next-iq3_xxs-rope-scaling",
+ "lib_dirs": [
+  "/usr/local/cuda/bin",
+  "/usr/local/cuda/lib64"
+ ],
+ "port": 8130,
+ "args": [
+  "--pack",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/packs/iq3_xxs",
+  "--native",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/models/IQ3_XXS/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00001-of-00002.gguf",
+  "--ple-gguf",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/models/IQ3_XXS/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00002-of-00002.gguf",
+  "--expert-profile",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata/data/expert-profile.bin",
+  "--expert-cache",
+  "auto",
+  "--prefill",
+  "auto",
+  "--spec",
+  "4",
+  "--spec-min-p",
+  "0.5",
+  "--mtp",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/mtp/rt",
+  "--kv",
+  "int8",
+  "--kv-resident",
+  "32768",
+  "--max-context",
+  "560000",
+  "--rope-scaling",
+  "linear",
+  "--rope-scale",
+  "2"
+ ],
+ "log": "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata/bench/results/2026-09-28-rope-scaling/engine-B-linear2-524288.log"
+}

bench/results/2026-09-28-rope-scaling/config-C-yarn2.json

@@ -0,0 +1,42 @@
+{
+ "exe": "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata/build/strata",
+ "cwd": "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata",
+ "tokenizer": "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/packs/iq3_xxs/tokenizer",
+ "model_name": "qwen3.8-flash-next-iq3_xxs-rope-scaling",
+ "lib_dirs": [
+  "/usr/local/cuda/bin",
+  "/usr/local/cuda/lib64"
+ ],
+ "port": 8130,
+ "args": [
+  "--pack",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/packs/iq3_xxs",
+  "--native",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/models/IQ3_XXS/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00001-of-00002.gguf",
+  "--ple-gguf",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/models/IQ3_XXS/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00002-of-00002.gguf",
+  "--expert-profile",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata/data/expert-profile.bin",
+  "--expert-cache",
+  "auto",
+  "--prefill",
+  "auto",
+  "--spec",
+  "4",
+  "--spec-min-p",
+  "0.5",
+  "--mtp",
+  "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata-data/mtp/rt",
+  "--kv",
+  "int8",
+  "--kv-resident",
+  "32768",
+  "--max-context",
+  "560000",
+  "--rope-scaling",
+  "yarn",
+  "--rope-scale",
+  "2"
+ ],
+ "log": "/home/jakub/workspace/deepseek-harness/harnes_workspace/Strata/bench/results/2026-09-28-rope-scaling/engine-C-yarn2-524288.log"
+}

bench/results/2026-09-28-rope-scaling/kv-sweep-tgs.json

@@ -0,0 +1,121 @@
+[
+ {
+  "length": "128k",
+  "round": 0,
+  "kind": "decode",
+  "prompt_tok": 128401,
+  "read": 52,
+  "gen": 357,
+  "read_tok_s": 79.2,
+  "gen_tok_s": 56.3,
+  "drafts_ok": 182,
+  "drafts_all": 305,
+  "seg_blocks": 3284340,
+  "seg_mib": 370.0,
+  "seg_misses": 91744,
+  "seg_hit_pct": 97.207,
+  "kib_per_token": 1061.29
+ },
+ {
+  "length": "128k",
+  "round": 1,
+  "kind": "read",
+  "prompt_tok": 128357,
+  "read": 128357,
+  "gen": 24,
+  "read_tok_s": 1389.2,
+  "gen_tok_s": 41.7,
+  "drafts_ok": 11,
+  "drafts_all": 23,
+  "seg_blocks": -3253560,
+  "seg_mib": -391.7,
+  "seg_misses": -97147,
+  "seg_hit_pct": 97.014,
+  "kib_per_token": -3.12
+ },
+ {
+  "length": "128k",
+  "round": 1,
+  "kind": "decode",
+  "prompt_tok": 128402,
+  "read": 52,
+  "gen": 388,
+  "read_tok_s": 76.5,
+  "gen_tok_s": 54.6,
+  "drafts_ok": 195,
+  "drafts_all": 363,
+  "seg_blocks": 3752616,
+  "seg_mib": 463.5,
+  "seg_misses": 114911,
+  "seg_hit_pct": 96.938,
+  "kib_per_token": 1223.26
+ },
+ {
+  "length": "512k",
+  "round": 0,
+  "kind": "read",
+  "prompt_tok": 522983,
+  "read": 522983,
+  "gen": 24,
+  "read_tok_s": 868.4,
+  "gen_tok_s": 42.4,
+  "drafts_ok": 13,
+  "drafts_all": 16,
+  "seg_blocks": -3808056,
+  "seg_mib": -387.8,
+  "seg_misses": -96113,
+  "seg_hit_pct": 97.476,
+  "kib_per_token": -0.76
+ },
+ {
+  "length": "512k",
+  "round": 0,
+  "kind": "decode",
+  "prompt_tok": 523028,
+  "read": 52,
+  "gen": 402,
+  "read_tok_s": 63.3,
+  "gen_tok_s": 48.4,
+  "drafts_ok": 221,
+  "drafts_all": 348,
+  "seg_blocks": 3580056,
+  "seg_mib": 920.4,
+  "seg_misses": 228658,
+  "seg_hit_pct": 93.613,
+  "kib_per_token": 2344.5
+ },
+ {
+  "length": "512k",
+  "round": 1,
+  "kind": "read",
+  "prompt_tok": 522984,
+  "read": 522984,
+  "gen": 24,
+  "read_tok_s": 857.1,
+  "gen_tok_s": 35.5,
+  "drafts_ok": 9,
+  "drafts_all": 18,
+  "seg_blocks": -3555408,
+  "seg_mib": -905.8,
+  "seg_misses": -225016,
+  "seg_hit_pct": 93.671,
+  "kib_per_token": -1.77
+ },
+ {
+  "length": "512k",
+  "round": 1,
+  "kind": "decode",
+  "prompt_tok": 523029,
+  "read": 52,
+  "gen": 402,
+  "read_tok_s": 61.3,
+  "gen_tok_s": 42.8,
+  "drafts_ok": 192,
+  "drafts_all": 388,
+  "seg_blocks": 4005216,
+  "seg_mib": 1079.9,
+  "seg_misses": 268221,
+  "seg_hit_pct": 93.303,
+  "kib_per_token": 2750.79
+ }
+]

bench/results/2026-09-28-rope-scaling/needle-A-none.json

@@ -0,0 +1,29 @@
+[
+ {
+  "length": "1k",
+  "depth": 50,
+  "prompt_tokens": 1442,
+  "seconds": 3.7,
+  "found": true,
+  "word": "meadow-copper-504",
+  "answer": "meadow-copper-504"
+ },
+ {
+  "length": "32k",
+  "depth": 50,
+  "prompt_tokens": 31763,
+  "seconds": 27.5,
+  "found": true,
+  "word": "falcon-quartz-940",
+  "answer": "falcon-quartz-940"
+ },
+ {
+  "length": "128k",
+  "depth": 50,
+  "prompt_tokens": 128328,
+  "seconds": 86.1,
+  "found": true,
+  "word": "willow-cobalt-696",
+  "answer": "willow-cobalt-696"
+ }
+]

bench/results/2026-09-28-rope-scaling/needle-B-linear2-512k.json

@@ -0,0 +1,11 @@
+[
+ {
+  "length": "512k",
+  "depth": 50,
+  "prompt_tokens": 527051,
+  "seconds": 619.0,
+  "found": true,
+  "word": "meadow-copper-504",
+  "answer": "meadow-copper-504"
+ }
+]

bench/results/2026-09-28-rope-scaling/needle-B-linear2.json

@@ -0,0 +1,16 @@
+[
+ {
+  "length": "262k",
+  "depth": 50,
+  "prompt_tokens": 274222,
+  "seconds": 232.2,
+  "found": true,
+  "word": "meadow-copper-504",
+  "answer": "meadow-copper-504"
+ },
+ {
+  "length": "512k",
+  "depth": 50,
+  "error": "HTTP Error 400: Bad Request"
+ }
+]

bench/results/2026-09-28-rope-scaling/needle-C-yarn2-rebased.json

@@ -0,0 +1,11 @@
+[
+ {
+  "length": "262k",
+  "depth": 50,
+  "prompt_tokens": 273708,
+  "seconds": 234.8,
+  "found": true,
+  "word": "meadow-copper-504",
+  "answer": "meadow-copper-504"
+ }
+]

bench/results/2026-09-28-rope-scaling/needle-C-yarn2.json

@@ -0,0 +1,20 @@
+[
+ {
+  "length": "262k",
+  "depth": 50,
+  "prompt_tokens": 274215,
+  "seconds": 235.5,
+  "found": true,
+  "word": "meadow-copper-504",
+  "answer": "meadow-copper-504"
+ },
+ {
+  "length": "512k",
+  "depth": 50,
+  "prompt_tokens": 526988,
+  "seconds": 615.0,
+  "found": true,
+  "word": "falcon-quartz-940",
+  "answer": "falcon-quartz-940"
+ }
+]

bench/results/2026-09-29-layer-split-limits/README.md

@@ -0,0 +1,59 @@
+# Layer split: the features that were off across GPUs (2026-09-29)
+
+**Setup:**
+- **Rig:** RIBPC. RTX 5080 16 GB (CUDA0) + RTX 3090 24 GB; RTX 2080 Ti 22 GB as a helper card. Ryzen 9 9950X3D,
+  62 GB RAM, Windows 11.
+- **Model:** the Coder (IQ1_M native pack).
+- **Build:** branch `mg/limits`, sm_75 + sm_86 + sm_120.
+- **Correctness runs:** `rib_norepeat.py`, with a fixed cache, no swaps, no PCIe share and no suffix drafts where two
+  runs are compared byte for byte.
+- **Speed runs:** `rib_pp.py`.
+- Raw results are in `data/`.
+
+## Correctness
+
+| Check | Result |
+|---|---|
+| One GPU, this branch vs the 0.1.21-equivalent run (fixed cache) | 10/10 byte-identical |
+| Speed projection (control vector), one GPU vs the split on the same GPU (K=24) | 10/10 byte-identical |
+| KV streaming (128K context, 32K resident), one GPU vs the split on the same GPU | 10/10 byte-identical |
+| Images, one GPU vs the split on the same GPU (three questions about a test picture) | identical answers |
+| Speed projection / KV streaming / plain, 5080 + 3090 (K=24): no-repeat under presence 100, the 144 sanity case | all pass, 0 repeats |
+| The vector acts across GPUs: 5080 + 3090 with vs without the vector | 8 of 10 answers differ (as on one GPU: 7 of 10) |
+| Images, 5080 + 3090 (K=24): "What color is the circle?" / "What number?" / describe | "Red" / "42" / "A red circle, the number 42, and a blue square are displayed on a white background" |
+| Mid-prompt checkpoint (every 16,384 tokens): a 19.5K prompt, then another sharing its first 18,600 tokens | one GPU and 5080 + 3090: reused 16,384, answer right |
+| 5080 + 3090 (K=30) + a 2080 Ti helper holding 3,000 experts | all pass |
+| `--mmap-experts` with the Coder (a native pack) | a clear start-up error: it needs a canonical pack's `experts.bin` (with or without a split) |
+
+Across GPUs the text is not byte-identical to one GPU: experts that one card leaves to the CPU run on a GPU in the
+split, and the two round differently.
+
+## Speed
+
+| Run | Prompt 16K / 28K / 60K tok/s | Decode story / code tok/s | Hits |
+|---|---|---|---|
+| KV streaming (128K), 5080 alone | 1,487 / 1,801 / 1,837 | 66.6 / 74.0 | 59-71% |
+| KV streaming (128K), 5080 + 3090 auto | 1,685 / 1,957 / 1,968 | 75.8 / 97.0 | 96-97% |
+| Speed projection, 5080 + 3090 auto | 1,813 / 2,053 / - | 77.0 / 103.6 | 96-97% |
+| 5080 + 3090 (K=30), no helper | - | 62.5 / 85.2 | |
+| 5080 + 3090 (K=30) + 2080 Ti helper | - | 43.0 / 63.7 | |
+
+**The helper card makes it slower,** as it did without a split (bench/results/2026-09-29-layer-split). Its per-layer
+round trip costs more than the CPU pool needs for the few experts it would take over. It stays supported: the
+helpers take the visible GPUs no stage runs on and hold only experts no stage's cache holds. But it isn't
+recommended.
+
+## What changed
+
+- **Per-device tables:** the image-position (mrope) table and the control vector's tables are now kept per device;
+  every stage's rope and steering kernels read their own device's copy. `cvec_set_enabled` switches the vector on
+  every device.
+- **KV streaming:** each stage's session streams its own KV host copy (pinned, portable). The split no longer forces
+  it off.
+- **Mid-prompt checkpoints:** `Prefill::on_stage_chunk` lets each stage save its part of a checkpoint when it has
+  read the chunk. The last stage assembles the parts: the earlier ones are a chunk ahead by then.
+- **Helpers (`--expert-cache-remote`) with a split:** they take the visible devices after the stages, skip every
+  pair a stage's cache holds, and preflight and open on those devices.
+- **Explicit `--expert-cache` with a split:** it is capped so CUDA0 keeps room for the prompt path's own buffers.
+  Without the cap, the first prompt failed with "device buffers ... do not fit".
+- **`--mmap-experts`:** refused at start for a native pack, with the reason.

bench/results/2026-09-29-layer-split-limits/data/norepeat-lim-cv-same24-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 102,
+  "drafts_offered": 166,
+  "tok_s": 66.7,
+  "text": "The wind didn\u2019t just howl; it screamed. It tore through the iron gallery of the Blackwood Point Light, rattling the glass panes like a prisoner testing the bars of a cell.\n\nElias Thorne was not a man who feared the dark. He was a man who feared the silence.\n\nFor forty years, he had lived in the shadow of the Fresnel lens, a rotating eye of glass and brass that swept the Atlantic with a beam of pure, unyielding light. His job was simple: keep the light burning. Keep the logbook current. Keep the foghorn sounding when the mist rolled in, thick as wool.\n\nBut Elias knew something else. He knew that the light was not just for ships. It was for the lost.\n\nIt was November 14th, 1982. The storm was a Category 5, a monster that had swallowed the horizon. The waves were mountains of black water, crashing against the granite"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 134,
+  "drafts_offered": 180,
+  "tok_s": 80.8,
+  "text": "```python\nimport csv\nfrom typing import List, Dict\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, str]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 72.5,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 74.6,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 104,
+  "repeats": 0,
+  "drafts_accepted": 29,
+  "drafts_offered": 92,
+  "tok_s": 45.4,
+  "text": "Aardvark  \nAlbatross  \n\nAlligator   \nAnaconda    \nAntelope     \nBaboon       \nBadger      \nBat         \nBear        \nBeaver          \nBirds of Paradise (Manucode) \nBoa Constrictor \n\nBuffalo           \nCamel            \nCapybara             \nCat              \nChameleon\nCheetah\n\nChicken\n\n\nCrocodile  \nDeer  \n\nDingo   \nDog    \nDonkey     \nDragonfly   \n\nElephant       \nEmu      \nFalcon        \nFerret          \nFlamingo         \nFox<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 72,
+  "repeats": 0,
+  "drafts_accepted": 15,
+  "drafts_offered": 70,
+  "tok_s": 46.1,
+  "text": "The wind didn\u2019t just howl; it screamed against the glass of Lantern House 42, demanding entry into every crack and crevice that had been sealed with tar in previous years but now wept like old wounds on an open sore skin\u2014like a wound left unhealed by time. Elias knew this rhythm better than he remembered his own name<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 26,
+  "drafts_offered": 76,
+  "tok_s": 49.3,
+  "text": "The wind didn\u2019t just blow at Blackwood Rock; it screamed through the gaps in my teeth, searching for something to break its rhythm against stone that refused be broken by anything less than God himself had forged into being willing and able withstand eternity\u2019s cruelty without complaint or mercy from start finish until now forevermore if any such concept even existed within human comprehension let alone divine authority which we all knew did not exist but wished it would because wishful thinking is always easier to imagine hopelessly impossible truths as probable lies than vice versa.\n\nElias Thorne was eighty-three years old today, exactly one hundred and forty-seven days since his last heart attack had been logged by Dr Armitage who himself retired seven months ago after receiving a subpoena from the county clerk indicating he might have overstayed professional courtesy boundaries"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 94,
+  "repeats": 0,
+  "drafts_accepted": 27,
+  "drafts_offered": 56,
+  "tok_s": 46.7,
+  "text": "Lion  \nTiger   \nElephant \nGiraffe    \nZebra     \nPanda       \nKangaroo      \nKoala        \nHippo         \nRhino          \nCheetah            \nLeopard           \nJaguar             \nWolf                \nFox              \nBear               \nDeer                 \nElk                  \nMoose                    \nBuffalo                        \nCamel                       \nDonkey                      \nGoat                     \nSheep                   \nCow                         \nBull                          \nOx                           \nPig                            \nBoar                             \nRabbit                              \nSquirrel                                <|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 13,
+  "tok_s": 62.4,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 37,
+  "drafts_offered": 148,
+  "tok_s": 56.4,
+  "text": "The phrase \"the History Of The Sea\" is inherently ambiguous, as it could refer to several distinct historical narratives: geological formation (how oceans came into existence), maritime navigation and exploration by humans throughout human civilization; or perhaps more specifically in modern times refers often used metaphorically for economic trends like stock market fluctuations (\"sea change\"). However given your request likely intends an academic-style comprehensive overview covering both natural science aspects AND cultural significance through time periods\u2014especially since this kind question appears frequently on exams asking students write essays discussing evolution from primordial origins up present-day impacts including environmental changes due climate crisis etc.\u2014I will craft such broad yet structured piece combining geology + anthropology/ecological impact together while maintaining coherent flow suitable high-level educational context without overly technical jargon but still accurate enough scientifically grounded facts where appropriate within reasonable scope limits typical school assignments expect (~80\u201312% word count range implied implicitly though not stated explicitly here we aim moderate length ~65 words? Wait no user said \u201clong\u201d so probably >3k+ characters minimum safe bet around 7-9 paragraphs total approximating maybe close-to-full-page standard double-spaced equivalent which translates roughly \u22654K chars safely acceptable). Let me proceed accordingly ensuring clarity structure intro body conclusion style formal tone neutral informative balanced perspective acknowledging uncertainties if any minor ones exist e.g exact dates vary depending sources hence use hedging language sparingly only when necessary avoid overclaiming certainty especially regarding speculative theories vs established consensus knowledge base current mainstream understanding circa early-mid"
+ }
+]

bench/results/2026-09-29-layer-split-limits/data/norepeat-lim-cv-single-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 102,
+  "drafts_offered": 166,
+  "tok_s": 67.1,
+  "text": "The wind didn\u2019t just howl; it screamed. It tore through the iron gallery of the Blackwood Point Light, rattling the glass panes like a prisoner testing the bars of a cell.\n\nElias Thorne was not a man who feared the dark. He was a man who feared the silence.\n\nFor forty years, he had lived in the shadow of the Fresnel lens, a rotating eye of glass and brass that swept the Atlantic with a beam of pure, unyielding light. His job was simple: keep the light burning. Keep the logbook current. Keep the foghorn sounding when the mist rolled in, thick as wool.\n\nBut Elias knew something else. He knew that the light was not just for ships. It was for the lost.\n\nIt was November 14th, 1982. The storm was a Category 5, a monster that had swallowed the horizon. The waves were mountains of black water, crashing against the granite"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 134,
+  "drafts_offered": 180,
+  "tok_s": 81.0,
+  "text": "```python\nimport csv\nfrom typing import List, Dict\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, str]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 62.4,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 73.4,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 104,
+  "repeats": 0,
+  "drafts_accepted": 29,
+  "drafts_offered": 92,
+  "tok_s": 43.5,
+  "text": "Aardvark  \nAlbatross  \n\nAlligator   \nAnaconda    \nAntelope     \nBaboon       \nBadger      \nBat         \nBear        \nBeaver          \nBirds of Paradise (Manucode) \nBoa Constrictor \n\nBuffalo           \nCamel            \nCapybara             \nCat              \nChameleon\nCheetah\n\nChicken\n\n\nCrocodile  \nDeer  \n\nDingo   \nDog    \nDonkey     \nDragonfly   \n\nElephant       \nEmu      \nFalcon        \nFerret          \nFlamingo         \nFox<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 72,
+  "repeats": 0,
+  "drafts_accepted": 15,
+  "drafts_offered": 70,
+  "tok_s": 46.1,
+  "text": "The wind didn\u2019t just howl; it screamed against the glass of Lantern House 42, demanding entry into every crack and crevice that had been sealed with tar in previous years but now wept like old wounds on an open sore skin\u2014like a wound left unhealed by time. Elias knew this rhythm better than he remembered his own name<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 26,
+  "drafts_offered": 76,
+  "tok_s": 48.9,
+  "text": "The wind didn\u2019t just blow at Blackwood Rock; it screamed through the gaps in my teeth, searching for something to break its rhythm against stone that refused be broken by anything less than God himself had forged into being willing and able withstand eternity\u2019s cruelty without complaint or mercy from start finish until now forevermore if any such concept even existed within human comprehension let alone divine authority which we all knew did not exist but wished it would because wishful thinking is always easier to imagine hopelessly impossible truths as probable lies than vice versa.\n\nElias Thorne was eighty-three years old today, exactly one hundred and forty-seven days since his last heart attack had been logged by Dr Armitage who himself retired seven months ago after receiving a subpoena from the county clerk indicating he might have overstayed professional courtesy boundaries"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 94,
+  "repeats": 0,
+  "drafts_accepted": 27,
+  "drafts_offered": 56,
+  "tok_s": 46.8,
+  "text": "Lion  \nTiger   \nElephant \nGiraffe    \nZebra     \nPanda       \nKangaroo      \nKoala        \nHippo         \nRhino          \nCheetah            \nLeopard           \nJaguar             \nWolf                \nFox              \nBear               \nDeer                 \nElk                  \nMoose                    \nBuffalo                        \nCamel                       \nDonkey                      \nGoat                     \nSheep                   \nCow                         \nBull                          \nOx                           \nPig                            \nBoar                             \nRabbit                              \nSquirrel                                <|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 13,
+  "tok_s": 63.1,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 37,
+  "drafts_offered": 148,
+  "tok_s": 56.6,
+  "text": "The phrase \"the History Of The Sea\" is inherently ambiguous, as it could refer to several distinct historical narratives: geological formation (how oceans came into existence), maritime navigation and exploration by humans throughout human civilization; or perhaps more specifically in modern times refers often used metaphorically for economic trends like stock market fluctuations (\"sea change\"). However given your request likely intends an academic-style comprehensive overview covering both natural science aspects AND cultural significance through time periods\u2014especially since this kind question appears frequently on exams asking students write essays discussing evolution from primordial origins up present-day impacts including environmental changes due climate crisis etc.\u2014I will craft such broad yet structured piece combining geology + anthropology/ecological impact together while maintaining coherent flow suitable high-level educational context without overly technical jargon but still accurate enough scientifically grounded facts where appropriate within reasonable scope limits typical school assignments expect (~80\u201312% word count range implied implicitly though not stated explicitly here we aim moderate length ~65 words? Wait no user said \u201clong\u201d so probably >3k+ characters minimum safe bet around 7-9 paragraphs total approximating maybe close-to-full-page standard double-spaced equivalent which translates roughly \u22654K chars safely acceptable). Let me proceed accordingly ensuring clarity structure intro body conclusion style formal tone neutral informative balanced perspective acknowledging uncertainties if any minor ones exist e.g exact dates vary depending sources hence use hedging language sparingly only when necessary avoid overclaiming certainty especially regarding speculative theories vs established consensus knowledge base current mainstream understanding circa early-mid"
+ }
+]

bench/results/2026-09-29-layer-split-limits/data/norepeat-lim-cv-x2-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 85,
+  "drafts_offered": 172,
+  "tok_s": 36.6,
+  "text": "The wind didn\u2019t just howl; it screamed. It tore through the gaps in the iron railing of the Lantern Room, carrying the scent of brine and rotting kelp. Elias pulled his woolen collar up to his chin, his fingers numb and clumsy inside thick leather gloves.\n\nHe was the last man on the island. The automated systems had failed three winters ago, a glitch in the solar-powered backup that no engineer had been able to fix before the supply boat stopped coming. Now, it was just him, the light, and the sea.\n\nElias climbed the spiral stairs, his boots heavy with salt spray. The iron steps groaned under his weight, a sound that seemed to mock the storm outside. He reached the top, the glass walls vibrating with the force of the gale. Outside, the world was a blur of black and white. The ocean was invisible; it was only a presence, a weight pressing against the stone foundation of the tower.\n\nHe"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 136,
+  "drafts_offered": 173,
+  "tok_s": 96.8,
+  "text": "```python\nimport csv\nfrom typing import List, Dict\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, str]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 88.7,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 94.1,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 104,
+  "repeats": 0,
+  "drafts_accepted": 30,
+  "drafts_offered": 96,
+  "tok_s": 55.9,
+  "text": "Aardvark  \nAlbatross  \n\nAlligator   \nAnaconda    \nAntelope     \nBaboon       \nBadger      \nBat         \nBear        \nBeaver          \nBirds of Paradise (Manucode) \nBoa Constrictor \n\nBuffalo           \nCamel            \nCapybara             \nCat              \nChameleon\nCheetah\n\nChicken\n\n\nCrocodile  \nDeer  \n\nDingo   \nDog    \nDonkey     \nDragonfly   \n\nElephant       \nEmu      \nFalcon        \nFerret          \nFlamingo         \nFox<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 29,
+  "drafts_offered": 114,
+  "tok_s": 55.4,
+  "text": "The wind didn\u2019t just howl; it screamed against the glass of Lantern House 42, demanding entry into every crack and crevice that had been sealed with tar in previous years but now wept like old wounds at this one\u2019s age: forty-three winters since its construction. My name was Elias Thorne\u2014no middle initial\u2014and I kept no logbook for visitors because there were none; only ships passed by, their hulls cutting through the black water as if they too feared what lay beneath it more than above or beside them in fog so thick that even my own reflection vanished from sight when looked upon directly.\n\nI climbed each morning not to greet dawn but check whether light still lived within me\u2014the bulb\u2019s heart had failed twice before, once during a storm named *Harrow*,"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 29,
+  "drafts_offered": 110,
+  "tok_s": 52.2,
+  "text": "The wind didn\u2019t just blow at Blackwood Rock; it screamed through the gaps in my teeth, searching for something to hold onto until I died.\u201d said Elias Thorne as he adjusted his collar against November\u2019s bite.** He was not merely complaining of cold weather but articulating a poetic metaphor: that even after death (metaphorically), there would be no relief from this relentless gale.\n\nElias had been the last human keeper on any significant stretch coast since automation became standard practice, yet here he stood , stubbornly refusing to let technology replace his vigilance . His cottage perched atop a crumbling granite foundation was more than just shelter; it housed centuries of handwritten logs detailing every ship\u2019s name and cargo load that passed within sight.\n\nOn most nights Elias tended the light mechanically\u2014"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 91,
+  "repeats": 0,
+  "drafts_accepted": 29,
+  "drafts_offered": 69,
+  "tok_s": 58.7,
+  "text": "Lion  \nTiger   \nElephant \nGiraffe    \nZebra     \nPanda       \nKangaroo      \nKoala        \nHippopotamus          \nRhinoceros            \nLeopard                \nCheetah                 \nPanther                  \nWolf                    \nFox                      \nBear                     \nDeer                       \nElk                        \nMoose               \nBuffalo                   \nCamel           \nDonkey              \nGoat             \nSheep         \nCow  \nBull   \nOx    \nPig     \nDog       \nCat<|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 12,
+  "repeats": 0,
+  "drafts_accepted": 4,
+  "drafts_offered": 17,
+  "tok_s": 60.3,
+  "text": "1 2,3456789<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 41,
+  "drafts_offered": 168,
+  "tok_s": 59.9,
+  "text": "The phrase \"the History Of The Sea\" is inherently ambiguous, as it could refer to several distinct historical narratives: geological formation (how oceans came into existence), maritime navigation and exploration histories (\"history at/over/across/on/in/of/to/from/toward/off by means around above below through under upon alongside against among between within without throughout despite during after before since until while when where who whom whose which what how why whether\"), or perhaps even metaphorical interpretations involving human interaction with water bodies over time periods like ages eras epochs generations centuries decades years months days hours minutes seconds moments instants times occasions instances events episodes incidents occurrences situations circumstances conditions states phases stages steps processes procedures sequences series chains cycles loops repetitions iterations continuations progressions developments evolutions transformations changes alterations modifications adjustments corrections revisions amendments updates upgrades improvements enhancements refinements optimizations perfecting completing finishing concluding ending terminating ceasing stopping halting pausing resuming continuing proceeding advancing progressing moving shifting translating rotating reflecting mirroring flipping turning twisting bending curving arches spirals helix coils twists turns rotations reflections mirrors flips inversions reversings reversion backtracking retracing reversing undo redo do again repeat repeats repeated repeatedly repetition repetitive repetitiveness repete repeater repeatingly recurrent recurrence recurring recurs recur recurred recursion recursive recursively recurse recessed recessionary regress regression regressed retrograde reverse reversed reversal revert reverted reverberate resonated echo echoed echoing echoes echolocation sonar radar radio telecommunication communication communications communicate communicated communicating communicative comms comm chatter chat chats chatting chatted talk talks talked"
+ }
+]

bench/results/2026-09-29-layer-split-limits/data/norepeat-lim-hp0-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 88,
+  "drafts_offered": 171,
+  "tok_s": 62.5,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his woolen collar up to his chin, the rough fabric scratching against his stubble. Outside the thick, salt-crusted glass of the lantern room, the Atlantic was a churning cauldron of black and white foam. Rain lashed against the panes in horizontal sheets, blurring the world into a smear of gray and shadow.\n\nInside, however, it was warm. The smell of kerosene and old wood hung heavy in the air, a scent that had defined his life for thirty years.\n\nElias was not a man of many words. He was a man of many tasks. His hands, mapped with scars from broken glass and rusted iron, moved with a rhythm that predated his memory. He checked the clockwork mechanism of the Fresnel lens, ensuring the rotation was smooth, silent, and precise. *Tick. Tick. Tick.* The sound was the heartbeat of the coast."
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 135,
+  "drafts_offered": 184,
+  "tok_s": 85.2,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 78.1,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 80.5,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 59,
+  "repeats": 0,
+  "drafts_accepted": 13,
+  "drafts_offered": 48,
+  "tok_s": 46.6,
+  "text": "Aardvark  \nAlbatross  \n\nAlligator   \nAntelope    \nBaboon      \nBadger     \nBeaver       \nBear        \nBird         \nBuffalo     \n\nCat          \nCheetah      \n\nChimpanzee \nClam         \n\n\nCrocodile   \n\n\n\nDolphin      \n\n\n\n\nDonkey       <|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 30,
+  "drafts_offered": 101,
+  "tok_s": 51.3,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty cathedral vaults below Elias\u2019s boots smelled faintly brine and old coffee as he climbed spiral stairs worn smooth by decades feet his hands were calloused from gripping iron railings that had been polished to a dull shine\n\nElias was not merely keeping light alive; He kept order intact. Every night, at precisely 18:07 hours local time\u2014adjusted for leap seconds and magnetic drift\u2014he wound the clockwork mechanism inside brass housing behind Fresnel lens This wasn\u2019t vanity It\u2019s necessity The rotation speed must remain constant or ships lose their bearing in fog where compasses fail\n\nHe spoke softly to himself while working, murmuring numbers aloud because silence made him"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 67,
+  "repeats": 0,
+  "drafts_accepted": 14,
+  "drafts_offered": 68,
+  "tok_s": 41.2,
+  "text": "The wind didn\u2019t just blow at Blackwood Rock; it screamed through the gaps in his teeth, like he had no mouth to hold back its fury anymore that night.\u201d Elara pulled her wool coat tighter around herself as she climbed spiral staircase of **Blackrock Lighthouse**. Her boots were slick with salt spray from previous days.<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 91,
+  "repeats": 0,
+  "drafts_accepted": 26,
+  "drafts_offered": 54,
+  "tok_s": 48.8,
+  "text": "Lion  \nTiger   \nElephant \nGiraffe    \nZebra     \nPanda       \nKoala      \nKangaroo        \nHippopotamus          \nRhinoceros            \nCamel                 \nCheetah               \nLeopard                \nJaguar                  \nBear                    \nWolf                     \nFox                      \nDog                       \nCat                        \nMouse                   \nRat                         \nSquirrel              \nDeer                      \n\nAntelope                \n\nBuffalo                 \n\n\nBison                   \n\n\n\nElk                    \n\n\n\n\nMoose                  <|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 11,
+  "tok_s": 68.8,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 32,
+  "drafts_offered": 107,
+  "tok_s": 52.3,
+  "text": "The ocean is not merely water; it has been, and remains to this day one giant storybook that weaves together geology with biology as wellas human culture into an epic narrative spanning billions years from its earliest beginnings in primordial times through modern-day ecological crises The vast expanse covers more than seventy percent Earth\u2019s surface area making up nearly all life support systems on our planet yet despite being so large humans have only explored less five thousand square kilometers out total 361 million km\u00b2 which means over ninety-nine point nine eight six per cent unexplored territory This makes oceans arguably larger unknown territories compared space exploration where NASA estimates they\u2019ve mapped roughly ten billion stars versus current marine surveys covering just two hundred fifty-six species documented globally against estimated millions undiscovered organisms including deep-sea creatures like anglerfish or vampire squid whose existence was first recorded centuries ago but still remain poorly understood due extreme pressures depths exceeding eleven miles below Pacific Trenches Mariana located near Guam island chain reaching maximum depth known today at approximately thirty-seven feet under pressure equivalent atmospheric levels causing structural collapse if unprotected by specialized vessels capable handling such conditions without failure mechanisms designed specifically for submersible operations operating within these zones require titanium hulls rated withstand forces greater gravity acting upon objects falling vertically downward acceleration rates calculated using Newtonian physics principles applied universally across gravitational fields regardless medium density variations present throughout different layers stratosphere troposphere mesospheres thermoclines etceterally speaking however when discussing aquatic environments instead air masses replace gases dissolved oxygen nitrogen arg"
+ }
+]

bench/results/2026-09-29-layer-split-limits/data/norepeat-lim-hp1-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 94,
+  "drafts_offered": 169,
+  "tok_s": 43.0,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was seventy-three years old, and he had been the keeper of the Blackwood Point Light for forty of those years. The other thirty-three had been spent in a small, drafty cottage that smelled perpetually of kerosene and damp wood.\n\nFor decades, Elias had tended the great Fresnel lens, polishing the glass prisms until they gleamed like diamonds, winding the clockwork mechanism that turned the beam, and trimming the wick of the oil lamp. It was a job of patience, of precision, of silence. The light was his charge. The sea was his neighbor.\n\nBut this morning, the sea was not his neighbor. It was his enemy.\n\nThe storm had been forecasted for three days, but it had arrived in one. The barometric pressure had dropped so sharply that Elias\u2019s ears popped."
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 136,
+  "drafts_offered": 178,
+  "tok_s": 63.7,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 56.8,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 57.7,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 94,
+  "repeats": 0,
+  "drafts_accepted": 24,
+  "drafts_offered": 49,
+  "tok_s": 43.3,
+  "text": "Lion  \nTiger   \nElephant    \nGiraffe     \nZebra       \nHippopotamus \nRhinoceros      \nCheetah         \nLeopard        \nJaguar          \nPuma           \nWolf            \nFox             \nBear              \nDeer                \nElk                 \nMoose               \nAntelope                  \nBison                   \nBuffalo                    \nCamel                     \nDonkey                      \nGoat                       \nSheep                        \nCow                         \nDog                          \nCat                           \nRabbit                            \nMouse                             \nHamster                               \nGuinea Pig<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 35,
+  "drafts_offered": 108,
+  "tok_s": 41.4,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty cathedral vaults below Elias\u2019s boots smelled faintly brine and old coffee as he climbed spiral stairs worn smooth by decades feet his hands were calloused from gripping iron railings that had been polished to a dull shine.\n\nElias wasn\u2019t just keeping light; was guarding silence the beam swept across black water every seven seconds cutting through fog so thick it swallowed sound entirely for three nights straight no ships answered its signal not even fishing trawlers seeking shelter they\u2019d long abandoned this stretch of coast where currents shifted unpredictably pulling debris from sunken wrecks into tangled heaps that snagged anchors and tore hulls open like wounds.\n\nHe remembered the last time someone had"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 59,
+  "repeats": 0,
+  "drafts_accepted": 11,
+  "drafts_offered": 46,
+  "tok_s": 33.7,
+  "text": "The wind didn\u2019t just blow at Blackwood Rock; it screamed through the gaps in his teeth, trying to pry them apart like loose planks of weathered oak outside your own mouth again and then you are going away from home is fine but for now let me write a proper story.<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 60,
+  "repeats": 0,
+  "drafts_accepted": 17,
+  "drafts_offered": 48,
+  "tok_s": 43.2,
+  "text": "Aardvark  \nAntelope allonax (Oryx) \u2013 *Note: Using standard names for clarity*  \n\nLet me provide a clean list of exactly **1** animal name on each single physical text file/terminal output stream with no other characters except the newline (\\n).<|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 11,
+  "tok_s": 48.9,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 27,
+  "drafts_offered": 105,
+  "tok_s": 40.2,
+  "text": "The ocean is not merely water; it has been, and remains to this day one giant machine for making life possible on Earth.\" \u2014 *David Attenborough* \n\nThis quote captures perhaps more than any other single sentence in human language: that which we call \"the Sea\" or \u201cOcean\u201d was never just an element\u2014it became civilization itself through its capacity as both barrier (to land) but also conduit between lands\u2014and thus gave rise directly from being part nature\u2019s own evolutionary engine into becoming humanity's greatest historical actor across all time scales since first emergence until now present-day future projections still ongoing today within our current era context window limits allowed here by system constraints set above threshold levels required before output generation begins below line break marker inserted immediately after final punctuation mark ending entire preceding paragraph block structure defined earlier during initial drafting phase prior execution stage completed successfully without errors detected internally via internal validation routines executed automatically upon completion cycle termination signal received end-of-file condition triggered correctly according standard protocol specifications followed strictly adhered-to throughout process flow control logic implemented using structured programming constructs compatible with target runtime environment configuration parameters specified herein explicitly declared beforehand at top-level scope declaration section located near beginning source code file header comments included inline documentation style guidelines observed consistently applied uniformly everywhere else similarly formatted sections appearing later down document body text area scrolling vertically downward directionally aligned left margin justified right edge wrapped around fixed-width column boundaries determined dynamically based available screen real estate measured pixel-per-unit scaling factor adjusted responsively depending viewport dimensions reported back client-side rendering pipeline components responsible"
+ }
+]

bench/results/2026-09-29-layer-split-limits/data/norepeat-lim-kv-same24-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 94,
+  "drafts_offered": 167,
+  "tok_s": 62.7,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his woolen collar up to his chin, the fabric stiff with salt and ice. Outside the thick glass of the lantern room, the Atlantic was a churning cauldron of black and white, the waves crashing against the granite base with a violence that shook the very foundations of the tower. It was November, 1924, and the storm had been raging for three days.\n\nElias was not a man who feared the dark. He was a man who feared the silence.\n\nHe checked the clock on the wall. 11:42 PM. The rotation of the great Fresnel lens was steady, a rhythmic *whirrr-click, whirrr-click* that seemed to hold the chaos of the ocean at bay. The beam swept out, a blade of pure, concentrated light cutting through the rain and sleet, illuminating the jagged teeth of the reef below.\n\n"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 136,
+  "drafts_offered": 179,
+  "tok_s": 81.3,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 71.0,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 71.9,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 61,
+  "repeats": 0,
+  "drafts_accepted": 18,
+  "drafts_offered": 52,
+  "tok_s": 47.9,
+  "text": "Aardvark  \nAlbatross  \n\nAlligator   \nAntelope    \nBaboon      \nBadger     \nBeaver       \nBear        \nBird         \nBoar          \nBuffalo \nButterfly \n\nCamel           \nCat            \nCheetah        \n\nDolphin         \n\n\nElephant        \n\n\n\nFalcon          <|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 29,
+  "drafts_offered": 122,
+  "tok_s": 47.4,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty cathedral vaults below Elias\u2019s boots were heavy with salt and exhaustion as he climbed one hundred twelve steps to reach his post at dawn every morning for thirty years. His name was written on a brass plaque by door: **Elias Thorne**.\n\nHe wasn\u2019t just keeping light; He kept time, weathered hands gripping the cold iron railing until knuckles turned white against frostbite and windburn that never healed fully because they were always there waiting to be felt again when he stepped outside into storm or calm alike. The lens above him was a Fresnel giant\u2019s eye made of hand-ground crystal prisms each one polished daily with chamois cloth soaked in whale"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 65,
+  "repeats": 0,
+  "drafts_accepted": 11,
+  "drafts_offered": 58,
+  "tok_s": 42.6,
+  "text": "The wind didn\u2019t just blow at Cape Hollow; it screamed through the gaps in my cottage\u2019s shutters, rattling them like loose teeth until they slammed against their hinges every night for eleven months of winter and summer alike.\u201d I had never seen calm water here\u2014only gray churning seas that swallowed ships smaller than themselves<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 101,
+  "repeats": 0,
+  "drafts_accepted": 32,
+  "drafts_offered": 53,
+  "tok_s": 49.4,
+  "text": "Lion  \nTiger   \nElephant \nGiraffe    \nZebra     \nPanda       \nKoala      \nKangaroo        \nCheetah         \nHippopotamus          \nRhinoceros            \nLeopard             \nJaguar              \nWolf                \nFox                 \nBear                  \nDeer                    \nOtter                   \nBeaver                      \nBadger                        \nMongoose                          \nMeerkat                           \nHyena                             \nJackal                            \nAntelope                              \nBison                               \nElk                                 \nCaribou                                   \nLlama                                    \nAlpace                                     <|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 12,
+  "tok_s": 64.7,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 52,
+  "drafts_offered": 148,
+  "tok_s": 49.9,
+  "text": "The ocean is not merely water; it has been, and remains to this day one giant machine for making life possible on Earth.\" \u2014 *David Attenborough* \n\nThis quote captures perhaps more than any other single sentence in human language: that which we call \"the Sea\" or \u201cOcean\u201d was never just an element within our planet\u2019s geography but rather its most fundamental biological engine\u2014a living system whose existence predates humanity by hundreds millions years yet continues shaping every aspect from climate regulation through evolutionary biology down even into modern industrial logistics today's global supply chains depend upon them directly indirectly via atmospheric pressure systems weather patterns migration routes food webs carbon cycles oxygen generation thermal buffering tidal forces salinity gradients depth stratification light attenuation currents circulation gyres upwelling zones thermoclines halothermics bathymetric features continental shelves abyssal plains trenching ridges volcanic arcs island formations atoll structures seamounts submarine canons canyon walls cliff faces overhang ledge platforms reef flats fore-reef back-lagoon inner-shelf outer-slope drop-offs pinnacle pinnacles spires columns arches tunnels caves grottos swim-through passages chimney vents blowholes fissures cracks crevices joints faults fractures breaks gaps holes openings void spaces hollow chambers cavernous interiors subterranean networks underground rivers lakes pools springs wells shaft pits sinks drains sewers pipes conduits tubes channels gutters ditches furrows grooves rills runnels streams brooks rivulets creeks tributaries branches forks splits divergences con"
+ }
+]

bench/results/2026-09-29-layer-split-limits/data/norepeat-lim-kv-single-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 94,
+  "drafts_offered": 167,
+  "tok_s": 49.2,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his woolen collar up to his chin, the fabric stiff with salt and ice. Outside the thick glass of the lantern room, the Atlantic was a churning cauldron of black and white, the waves crashing against the granite base with a violence that shook the very foundations of the tower. It was November, 1924, and the storm had been raging for three days.\n\nElias was not a man who feared the dark. He was a man who feared the silence.\n\nHe checked the clock on the wall. 11:42 PM. The rotation of the great Fresnel lens was steady, a rhythmic *whirrr-click, whirrr-click* that seemed to hold the chaos of the ocean at bay. The beam swept out, a blade of pure, concentrated light cutting through the rain and sleet, illuminating the jagged teeth of the reef below.\n\n"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 136,
+  "drafts_offered": 179,
+  "tok_s": 76.2,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 73.1,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 73.4,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 61,
+  "repeats": 0,
+  "drafts_accepted": 18,
+  "drafts_offered": 52,
+  "tok_s": 47.1,
+  "text": "Aardvark  \nAlbatross  \n\nAlligator   \nAntelope    \nBaboon      \nBadger     \nBeaver       \nBear        \nBird         \nBoar          \nBuffalo \nButterfly \n\nCamel           \nCat            \nCheetah        \n\nDolphin         \n\n\nElephant        \n\n\n\nFalcon          <|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 29,
+  "drafts_offered": 122,
+  "tok_s": 47.0,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty cathedral vaults below Elias\u2019s boots were heavy with salt and exhaustion as he climbed one hundred twelve steps to reach his post at dawn every morning for thirty years. His name was written on a brass plaque by door: **Elias Thorne**.\n\nHe wasn\u2019t just keeping light; He kept time, weathered hands gripping the cold iron railing until knuckles turned white against frostbite and windburn that never healed fully because they were always there waiting to be felt again when he stepped outside into storm or calm alike. The lens above him was a Fresnel giant\u2019s eye made of hand-ground crystal prisms each one polished daily with chamois cloth soaked in whale"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 65,
+  "repeats": 0,
+  "drafts_accepted": 11,
+  "drafts_offered": 58,
+  "tok_s": 42.3,
+  "text": "The wind didn\u2019t just blow at Cape Hollow; it screamed through the gaps in my cottage\u2019s shutters, rattling them like loose teeth until they slammed against their hinges every night for eleven months of winter and summer alike.\u201d I had never seen calm water here\u2014only gray churning seas that swallowed ships smaller than themselves<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 101,
+  "repeats": 0,
+  "drafts_accepted": 32,
+  "drafts_offered": 53,
+  "tok_s": 50.0,
+  "text": "Lion  \nTiger   \nElephant \nGiraffe    \nZebra     \nPanda       \nKoala      \nKangaroo        \nCheetah         \nHippopotamus          \nRhinoceros            \nLeopard             \nJaguar              \nWolf                \nFox                 \nBear                  \nDeer                    \nOtter                   \nBeaver                      \nBadger                        \nMongoose                          \nMeerkat                           \nHyena                             \nJackal                            \nAntelope                              \nBison                               \nElk                                 \nCaribou                                   \nLlama                                    \nAlpace                                     <|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 12,
+  "tok_s": 64.6,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 52,
+  "drafts_offered": 148,
+  "tok_s": 49.8,
+  "text": "The ocean is not merely water; it has been, and remains to this day one giant machine for making life possible on Earth.\" \u2014 *David Attenborough* \n\nThis quote captures perhaps more than any other single sentence in human language: that which we call \"the Sea\" or \u201cOcean\u201d was never just an element within our planet\u2019s geography but rather its most fundamental biological engine\u2014a living system whose existence predates humanity by hundreds millions years yet continues shaping every aspect from climate regulation through evolutionary biology down even into modern industrial logistics today's global supply chains depend upon them directly indirectly via atmospheric pressure systems weather patterns migration routes food webs carbon cycles oxygen generation thermal buffering tidal forces salinity gradients depth stratification light attenuation currents circulation gyres upwelling zones thermoclines halothermics bathymetric features continental shelves abyssal plains trenching ridges volcanic arcs island formations atoll structures seamounts submarine canons canyon walls cliff faces overhang ledge platforms reef flats fore-reef back-lagoon inner-shelf outer-slope drop-offs pinnacle pinnacles spires columns arches tunnels caves grottos swim-through passages chimney vents blowholes fissures cracks crevices joints faults fractures breaks gaps holes openings void spaces hollow chambers cavernous interiors subterranean networks underground rivers lakes pools springs wells shaft pits sinks drains sewers pipes conduits tubes channels gutters ditches furrows grooves rills runnels streams brooks rivulets creeks tributaries branches forks splits divergences con"
+ }
+]

bench/results/2026-09-29-layer-split-limits/data/norepeat-lim-kv-x2-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 97,
+  "drafts_offered": 176,
+  "tok_s": 73.0,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was the last of the line, the only man left on the jagged spine of Widow\u2019s Rock. For forty years, he had tended the light. For forty years, he had listened to the ocean\u2019s endless, hungry whisper.\n\nTonight was different. The storm wasn\u2019t just a storm; it was a *tempest*. The waves didn\u2019t crash; they *shattered*. They threw themselves against the granite base of the lighthouse with the force of a battering ram, sending tremors up through the soles of Elias\u2019s boots.\n\nHe climbed the spiral stairs, one hundred and twelve steps of iron and rust. His hand, calloused and scarred from decades of polishing the brass railing, found the familiar groove in the metal. He didn\u2019t look up. He didn\u2019t look down. He looked *forward*."
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 135,
+  "drafts_offered": 176,
+  "tok_s": 102.5,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 90.9,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 91.7,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 118,
+  "repeats": 0,
+  "drafts_accepted": 38,
+  "drafts_offered": 103,
+  "tok_s": 62.8,
+  "text": "Aardvark  \nAlbatross   \nAlligator    \nAntelope     \nBaboon       \nBadger      \nBeaver        \nBear          \nBird of Paradise \nBuffalo         \nCamel           \nCheetah            \nChimpanzee             \nCrane              \nCrocodile                \nDeer                 \nDolphin               \nDonkey                  \nElephant                   \nFlamingo                    \nFox                       \nGiraffe                     \nGoat                      \nHippopotamus  \nIguana       \nJaguar        \nKangaroo      \nKoala          \nLion         \nLeopard     \nMonkey    \nMoose   \nOstrich \nOtter\nPanda<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 58,
+  "repeats": 0,
+  "drafts_accepted": 9,
+  "drafts_offered": 63,
+  "tok_s": 50.4,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty jail cell below sea level three hundred feet down to where Elias kept his boots dry and ready for emergencies when he had no time even think about changing them.<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 140,
+  "repeats": 0,
+  "drafts_accepted": 22,
+  "drafts_offered": 90,
+  "tok_s": 50.1,
+  "text": "The wind didn\u2019t just blow at Blackwood Rock; it screamed through the gaps in his teeth, demanding entry into every crack and crevice of Stone Harbor Lighthous eKeepers have always been solitary figures against isolation\u2019s greatest adversary: time itself Elias Thorne knew this intimately. For thirty years he had kept watch over one hundred thousand ships each night scanning for lights that might signal disaster or hope\n\nHis job was simple but deadly serious He checked weather logs every day without fail The foghorn echoed through the tower three times before dawn Each morning at 4:02 AM Elias would climb eighty-two steps to reach his office where coffee cooled beside a single candle flickering in drafts from below<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 96,
+  "repeats": 0,
+  "drafts_accepted": 31,
+  "drafts_offered": 69,
+  "tok_s": 58.9,
+  "text": "Lion  \nTiger   \nElephant \nGiraffe    \nZebra     \nPanda       \nKangaroo      \nKoala        \nHippo         \nRhino          \nCheetah            \nLeopard             \nJaguar              \nPanther               \nCougar                \nBear                  \nWolf                    \nFox                     \nDeer                      \nElk                        \nMoose                       \nBison                         \nBuffalo                          \nAntelope                           \nCamel                            \nDonkey                              \nGoat                                \nSheep                                  \nCow                                    \nPig                                     \nHorse                                       <|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 13,
+  "tok_s": 71.2,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 37,
+  "drafts_offered": 119,
+  "tok_s": 61.3,
+  "text": "The ocean is not merely water; it has been, and remains to this day one giant machine for making life possible on Earth\u2019s surface.\u201d \u2014 *This quote by Rachel Carson serves as an apt introduction.* The story we tell today begins with that first drop falling into primordial pools billions years ago\u2014but what follows next? What happens when those drops become oceans themselves\u2014when they begin moving across continents carrying sediment from mountains down rivers until finally reaching their final resting place at last\u2014the deep abyssal plains where sunlight cannot reach nor pressure crushes everything else alive there below depths greater than six kilometers beneath waves crashing against shores above them all around world forever changing shape over time due plate tectonics shifting landmass slowly apart together again repeatedly throughout geological epochs spanning hundreds millions or even thousands million+ yrs since formation early Hadean era through Archeozoic eons onward present Holocene epoch still ongoing now right here under current conditions observed via satellites monitoring global climate patterns affecting currents temperatures salinity levels biodiversity distribution human impacts altering ecosystems directly indirectly causing extinction events locally globally recently historically prehistorically anciently mythologically culturally spiritually philosoph scientifically mathematically physically chem biol geo astro cosmological sociopolitical economic environmental ecological evolutionary genetic linguistic literary artistic musical cinematic theatrical photographic journalistic digital analog virtual real tangible intangible metaphysical ontosemantic semiotic symbolic allegorical narrative descriptive analytical interpretive evaluative critical reflective introspective contemplatory ponderous thoughtful considerate attentive observant perceptive insightful intelligent knowledgeable informed educated literati learned skilled capable"
+ }
+]

bench/results/2026-09-29-layer-split-limits/data/norepeat-lim-nocv-x2-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 87,
+  "drafts_offered": 170,
+  "tok_s": 71.4,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his woolen collar up to his chin, the rough fabric scratching against his stubble. Outside the thick, salt-crusted glass of the lantern room, the Atlantic was a churning cauldron of black and white foam. Rain lashed against the panes in horizontal sheets, blurring the world into a smear of gray and green.\n\nInside, however, it was warm. The smell of kerosene and old wood hung heavy in the air, a scent that had defined his life for thirty years.\n\nElias was not a man of many words. He was a man of many tasks. His hands, mapped with scars from rope burns and broken glass, moved with a rhythm that predated his memory. He checked the clockwork mechanism of the Fresnel lens, listening for the faint, rhythmic *tick-tick-tick* that signaled the rotation was true. If the rhythm faltered, ships"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 136,
+  "drafts_offered": 178,
+  "tok_s": 104.1,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 90.1,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 94.8,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 76,
+  "repeats": 0,
+  "drafts_accepted": 20,
+  "drafts_offered": 64,
+  "tok_s": 61.6,
+  "text": "Aardvark  \nAlbatross  \n\nAlligator   \nAntelope    \nBaboon      \nBadger     \nBeaver       \nBear         \nBird        \nBuffalo          \nButterfly \nCamel           \nCat            \nCaterpillar \n\nCentipede    \n\nChameleon   \n\nCheetah     \n\nChicken      \n\nCricket       \n\nCrocodile     \n\n\nDolphin       \n\n\n\nDonkey        \n\n\n\n\nDragon<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 21,
+  "drafts_offered": 90,
+  "tok_s": 59.2,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty jail cell below sea level to above cloud height at once\u2014no matter how high you climbed or deep into its foundations down through rock and saltwater. It was November again when Elias first noticed that his logbook had begun recording entries he hadn\u2019t written yet: *Storm surge expected Tuesday, but the sky is clear.*\n\nHe stopped writing for a moment to listen\u2014not with ears alone\u2014but by pressing both palms flat against cold iron walls where condensation formed in slow spirals like fingerprints left behind after touching something invisible. The metal hummed faintly beneath his skin as if remembering old storms long past their dates on paper calendars torn from newspapers dated three years ahead of today"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 17,
+  "drafts_offered": 63,
+  "tok_s": 52.6,
+  "text": "The wind didn\u2019t just blow at Blackwood Rock; it screamed through the gaps in his teeth, trying to get inside where he had spent thirty years refusing entry except for family and friends like him who were old enough too know better than young men ever could be again about what safety meant. It was November 2014 when Elias Thorne first stepped onto that spiral staircase with only one boot on because his other foot hurt after walking from the harbor office all morning long before anyone else thought he needed shoes off there for work even if nobody saw them do it but everyone knew why so they did not ask him anymore once this happened already twice last winter near same season now here again today too soon then tomorrow maybe never will come back unless someone sends message tonight via radio signal code Morse dot dash pattern"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 94,
+  "repeats": 0,
+  "drafts_accepted": 29,
+  "drafts_offered": 60,
+  "tok_s": 58.8,
+  "text": "Lion  \nTiger   \nElephant \nGiraffe    \nZebra     \nKangaroo       \nPanda        \nKoala          \nCheetah      \nWolf         \nFox           \nBear            \nMonkey             \nDolphin              \nWhale                \nShark                 \nOctopus               \nJellyfish                  \nCrab                    \nSpider                   \nRabbit                     \nCat                      \nDog                       \nHorse                        \nCow                          \nSheep                            \nGoat                              \nChicken                                \nRooster                                   \nTurkey                                  \nEagle                                    \nFalcon                                     <|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 13,
+  "tok_s": 71.8,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 52,
+  "drafts_offered": 148,
+  "tok_s": 61.8,
+  "text": "The ocean is not merely water; it has been, and remains to this day one giant machine for making life possible on Earth.\u201d \u2014 *David Attenborough* \n\nThis quote captures perhaps more than any other single sentence in human language: that which we call \u201cthe Sea\u201d or \"Ocean\" (terms often used interchangeably but distinct geographically) was never just an element within our planet\u2019s geography\u2014it became its engine itself\u2014a living system whose evolution shaped everything else around us from climate patterns down through evolutionary biology right up into modern civilization's economic structures cultural identities political boundaries ecological systems scientific understanding technological capabilities philosophical frameworks psychological experiences artistic expressions literary metaphors cinematic narratives musical compositions architectural designs urban planning strategies agricultural practices industrial processes medical discoveries legal precedents educational curricula religious traditions spiritual beliefs mythological stories folkloric tales poetic verses dramatic scripts visual arts photographic images digital media social networks behavioral norms emotional responses cognitive models decision-making algorithms predictive analytics statistical probabilities probabilistic reasoning causal inference counterfactual thinking hypothetical scenarios normative ethics deontal logic modal semantics temporal dynamics spatial relations topographical features hydrological cycles meteor phenomena atmospheric chemistry geological formations tectonic shifts volcanic eruptions seismic events tsunamis hurricanes cyclones monsoons typhoons droughts floods storms winds currents waves swells breakers surf foam spray mist fog rain snow ice glaciers berg floes drift pack-ice brine salinity pH alkalines acidity hardness softness temperature pressure depth light darkness color hue saturation brightness contrast luminance chroma tone value shade tint reflection"
+ }
+]

bench/results/2026-09-29-layer-split-limits/data/norepeat-lim-reg-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 88,
+  "drafts_offered": 187,
+  "tok_s": 58.7,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was seventy years old, but he moved with the grace of a man who had spent decades on a narrow spiral staircase. His hands, mapped with veins like the roots of an ancient oak, gripped the cold iron railing.\n\nFor forty years, Elias had tended the light at the end of the world. Not the end of the map, but the end of the land. Here, the Atlantic threw itself against the granite cliffs with such violence that the spray reached the gallery, thirty feet above the rocks.\n\nHe checked the clock. 11:42 PM. The fog was thickening, a gray soup that swallowed the horizon. In the old days, he would have climbed the stairs to the lantern room, polished the Fresnel lens, and wound the clockwork mechanism that turned the great beam. But the automation had changed"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 135,
+  "drafts_offered": 179,
+  "tok_s": 80.7,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 71.8,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 73.0,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 61,
+  "repeats": 0,
+  "drafts_accepted": 19,
+  "drafts_offered": 49,
+  "tok_s": 49.1,
+  "text": "Aardvark  \nAlbatross  \n\nAlligator   \nAntelope    \nBaboon      \nBadger     \nBeaver       \nBear        \nBird         \nBoar          \nBuffalo \nButterfly \n\nCamel           \nCat            \nCheetah        \n\nDolphin         \n\n\nElephant        \n\n\n\nFlamingo<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 80,
+  "repeats": 0,
+  "drafts_accepted": 6,
+  "drafts_offered": 52,
+  "tok_s": 46.2,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty cathedral hall outside my window at midnight on November third this year\u2014so I pulled up to check what was happening with that storm and why they were calling me out there when all we had left for tonight\u2019s shift is one last pass through our logs before dawn breaks.<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 17,
+  "drafts_offered": 83,
+  "tok_s": 43.9,
+  "text": "The wind didn\u2019t just blow at Cape Harrow; it screamed through the gaps in its teeth, hungry and relentless for three centuries of stone salt-spray history that had long since forgotten to be polite or gentle with itself against anything smaller than God Himself was willing acknowledge as divine protection from drowning souls who were already lost before they ever touched water.\n\nElias knew this rhythm better he himself could hear it sometimes; his boots worn smooth by pacing the spiral stair\u2019s center-post groove where thousands upon countless steps had rubbed away texture until all that remained beneath sole leather now felt like polished bone carved out slowly but surely over time into something more hollow than wood ever really should be allowed become when used so often enough within such confined circular spaces meant only for vertical ascent down always descending again back upward never truly leaving"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 62,
+  "repeats": 0,
+  "drafts_accepted": 18,
+  "drafts_offered": 31,
+  "tok_s": 49.1,
+  "text": "Lion  \nTiger  \n\nElephant  \n  \nGiraffe  \n\n\n\nHippopotamus    \nZebra   \nRhinoceros   \n\n\nPanda Bear    \n\n\n\n\nKangaroo     \nKoala      \nSloth      \n\n\n\n\n\nCheetah       \nLeopard        \nPanther        \n\n\n\n\n\n\nWolf              \nFox                \nBear                 <|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 13,
+  "tok_s": 62.7,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 47,
+  "drafts_offered": 153,
+  "tok_s": 52.2,
+  "text": "The ocean is not merely water; it has been, and remains to this day one giant machine for making life possible on Earth.\" \u2014 *David Attenborough* \n\nThis quote captures perhaps more than any other single sentence in human language: that which we call \"the Sea\" or \u201cOcean\u201d was never just an element within our planet\u2019s geography but rather its most fundamental biological engine\u2014a living system whose existence predates humanity by billions years yet continues shaping every aspect from climate regulation through evolutionary biology all way down modern industrial supply chains today's global shipping lanes carry cargo across vast distances because they were once crossed only slowly via coastal hopping routes used since antiquity until steamships revolutionized travel during late nineteenth century when diesel engines replaced wind power entirely allowing container ships carrying thousands TEUs (Twenty-foot Equivalent Units) per voyage crossing entire Pacific basins without stopping at intermediate ports anymore unlike earlier sailing vessels needing favorable winds currents seasonal patterns dictating departure windows based upon monsoon calendars established centuries ago before technological advances changed those constraints fundamentally altering logistics networks worldwide thereby transforming economic structures globally while simultaneously creating ecological disruptions due invasive species transported unintentionally alongside legitimate goods causing cascading ecosystem collapses locally where non-native organisms outcompete native fauna disrupting food webs leading population declines affecting biodiversity indices measured scientifically using standardized metrics like Shannon-Wiener diversity index calculations applied consistently over decades revealing trends showing significant decreases post-introduction events correl strongly with introduction dates matching historical records documenting first sightings confirmed taxonomically classified formally according International Code Nomenclature rules"
+ }
+]

bench/results/2026-09-29-layer-split-limits/data/pp-lim-cv-pp-x2.json

@@ -0,0 +1,84 @@
+{
+ "label": "lim-cv-pp-x2",
+ "extra": [
+  "--layer-split",
+  "auto",
+  "--control-vector-scaled",
+  "C:\\Users\\ribbon\\strata-test\\Strata\\data\\experimental-speed-projection\\Qwen3.8-Flash-Next-experimental-speed-projection.gguf:1.0",
+  "--control-vector-layer-range",
+  "4",
+  "44",
+  "--cvec-mode",
+  "project",
+  "--cvec-dir",
+  "per-layer"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 15925,
+   "prompt_ms": 8783.1,
+   "pp_tok_s": 1813.1,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27474,
+   "prompt_ms": 13379.7,
+   "pp_tok_s": 2053.4,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3652.4,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 246.8,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 77.0,
+   "reps": [
+    77.0
+   ],
+   "hit_rate": 0.9718150054476462,
+   "text": "The wind didn\u2019t just howl; it screamed. It tore through the gaps in the iron railing of the Lantern Room, carrying the scent of brine and rotting kelp. Elias pulled his woolen collar up to his chin, his fingers numb and clumsy inside thick leather gloves.\n\nHe was the last man on the island. The automated systems had failed three winters ago, a glitch in the solar panel array that no engineer had been able to fix before the supply boat stopped running. Now, it was just him, the light, and the sea.\n\nElias climbed the spiral stairs, his boots heavy with salt spray. The iron steps groaned under his weight, a sound that seemed to mock the storm outside. He reached the top, the glass walls vibrating with the force of the gale.\n\nInside the lantern room, the great Fresnel lens sat like a dormant eye. It was cold, dark, and waiting.\n\nElias moved to the control panel. His"
+  },
+  {
+   "name": "code",
+   "tok_s": 103.6,
+   "reps": [
+    103.6
+   ],
+   "hit_rate": 0.957731667226356,
+   "text": "```python\nimport csv\nfrom typing import List, Dict\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, str]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False"
+  }
+ ],
+ "stage_timing": [],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split auto)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: layer split auto: CUDA0 84 SMs at 2.81 GHz -> 0.31 ms per layer, 8.30 GiB for experts",
+  "strata generate: layer split auto: CUDA1 82 SMs at 1.86 GHz -> 0.48 ms per layer, 14.14 GiB for experts",
+  "strata generate: layer split auto: K=22 - predicted 19.7 ms per decode window; the caches hold 11298 of 12288 profiled pairs (~99.7% of the routed mass)",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 3479 slots, 6.22 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 22-47, expert cache 6656 slots (13.34 GiB), 6656 of its 6656 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-21",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-21 (CUDA0), 22-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 91.6% (5554 hits / 6062 lookups)",
+  "strata serve: decode expert cache hit rate: 95.3% (3592 hits / 3771 lookups)",
+  "strata serve: decode expert cache hit rate: 96.5% (3650 hits / 3782 lookups)",
+  "strata serve: decode expert cache hit rate: 96.3% (25027 hits / 25980 lookups)",
+  "strata serve: decode expert cache hit rate: 96.5% (3201 hits / 3318 lookups)",
+  "strata serve: decode expert cache hit rate: 97.2% (129334 hits / 133085 lookups)",
+  "strata serve: decode expert cache hit rate: 95.8% (108375 hits / 113158 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split-limits/data/pp-lim-kv-pp-single.json

@@ -0,0 +1,76 @@
+{
+ "label": "lim-kv-pp-single",
+ "extra": [
+  "--max-context",
+  "131072",
+  "--kv-resident",
+  "32768"
+ ],
+ "gpus": "0",
+ "needles": [
+  {
+   "tokens": 15925,
+   "prompt_ms": 10706.3,
+   "pp_tok_s": 1487.4,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27474,
+   "prompt_ms": 15256.7,
+   "pp_tok_s": 1800.8,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 59725,
+   "prompt_ms": 32515.5,
+   "pp_tok_s": 1836.8,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 4006.4,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 276.2,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 66.6,
+   "reps": [
+    66.6
+   ],
+   "hit_rate": 0.7101864314556545,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his woolen collar up to his chin, the fabric stiff with salt and ice. Outside the thick glass of the lantern room, the Atlantic was a churning cauldron of black and white, the waves crashing against the granite base with a violence that shook the very foundations of the tower. It was November, 1924, and the storm had been raging for three days.\n\nElias was not a man who feared the dark. He was a man who feared the silence.\n\nHe checked the clock on the wall. 11:42 PM. The rotation of the great Fresnel lens was steady, a rhythmic *whirrr-click, whirrr-click* that seemed to sync with his own heartbeat. He had been doing this for forty years. His hands were mapped with scars from rope burns and broken glass, his eyes permanently squinted against the glare of the bulb."
+  },
+  {
+   "name": "code",
+   "tok_s": 74.0,
+   "reps": [
+    74.0
+   ],
+   "hit_rate": 0.5873783774988882,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [],
+ "engine_lines": [
+  "strata generate: expert cache auto: 8.99 GiB free, 700 MiB reserved -> 3349 slots",
+  "strata generate: expert cache 2434 slots, 4.67 GiB of VRAM; policy is",
+  "strata serve: the prompt path borrows 1944 cache slots (3.72 GiB)",
+  "strata serve: decode expert cache hit rate: 41.8% (1746 hits / 4176 lookups)",
+  "strata serve: decode expert cache hit rate: 50.4% (1512 hits / 3000 lookups)",
+  "strata serve: decode expert cache hit rate: 54.9% (1689 hits / 3077 lookups)",
+  "strata serve: decode expert cache hit rate: 60.3% (1938 hits / 3213 lookups)",
+  "strata serve: decode expert cache hit rate: 58.3% (11146 hits / 19121 lookups)",
+  "strata serve: decode expert cache hit rate: 66.1% (2201 hits / 3331 lookups)",
+  "strata serve: decode expert cache hit rate: 71.0% (74397 hits / 104757 lookups)",
+  "strata serve: decode expert cache hit rate: 58.7% (54151 hits / 92191 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split-limits/data/pp-lim-kv-pp-x2.json

@@ -0,0 +1,87 @@
+{
+ "label": "lim-kv-pp-x2",
+ "extra": [
+  "--max-context",
+  "131072",
+  "--kv-resident",
+  "32768",
+  "--layer-split",
+  "auto"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 15925,
+   "prompt_ms": 9452.6,
+   "pp_tok_s": 1684.7,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27474,
+   "prompt_ms": 14042.4,
+   "pp_tok_s": 1956.5,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 59725,
+   "prompt_ms": 30345.9,
+   "pp_tok_s": 1968.1,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3806.1,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 245.6,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 75.8,
+   "reps": [
+    75.8
+   ],
+   "hit_rate": 0.9698055042592483,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his woolen collar up to his chin, the rough fabric scratching against his stubble. Outside the thick, salt-crusted glass of the lantern room, the Atlantic was a churning cauldron of black and white foam. Rain lashed against the panes in horizontal sheets, blurring the world into a smear of gray and shadow.\n\nInside, however, it was warm. The smell of kerosene and old wood hung heavy in the air, a scent that had defined Elias\u2019s life for thirty years. He stood before the great Fresnel lens, a cathedral of glass and brass that caught the light of the single, powerful bulb and fractured it into a thousand beams.\n\nHe checked the clock. 11:42 PM. The rotation was smooth, silent, a hypnotic sweep that painted the darkness with a slow, rhythmic pulse. *Flash. Dark. Flash. Dark.*\n\nE"
+  },
+  {
+   "name": "code",
+   "tok_s": 97.0,
+   "reps": [
+    97.0
+   ],
+   "hit_rate": 0.9562207324057541,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split auto)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 17.96 GiB free",
+  "strata generate: layer split auto: CUDA0 84 SMs at 2.81 GHz -> 0.31 ms per layer, 8.13 GiB for experts",
+  "strata generate: layer split auto: CUDA1 82 SMs at 1.86 GHz -> 0.48 ms per layer, 13.98 GiB for experts",
+  "strata generate: layer split auto: K=22 - predicted 19.7 ms per decode window; the caches hold 11199 of 12288 profiled pairs (~99.7% of the routed mass)",
+  "strata generate: expert cache auto: 10.30 GiB free, 700 MiB reserved -> 3277 slots",
+  "strata generate: expert cache 3409 slots, 6.09 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 22-47, expert cache 6656 slots (13.34 GiB), 6656 of its 6656 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-21",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-21 (CUDA0), 22-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 91.3% (5098 hits / 5585 lookups)",
+  "strata serve: decode expert cache hit rate: 94.7% (4000 hits / 4225 lookups)",
+  "strata serve: decode expert cache hit rate: 96.5% (4095 hits / 4245 lookups)",
+  "strata serve: decode expert cache hit rate: 97.8% (4183 hits / 4278 lookups)",
+  "strata serve: decode expert cache hit rate: 96.2% (27177 hits / 28250 lookups)",
+  "strata serve: decode expert cache hit rate: 97.6% (4177 hits / 4281 lookups)",
+  "strata serve: decode expert cache hit rate: 97.0% (130241 hits / 134296 lookups)",
+  "strata serve: decode expert cache hit rate: 95.6% (113534 hits / 118732 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split-limits/data/vision.json

@@ -0,0 +1,24 @@
+{
+ "answers": {
+  "single": [
+   " Red",
+   "42",
+   "A red circle, the number 42, and a blue square are arranged on a white background."
+  ],
+  "same24": [
+   " Red",
+   "42",
+   "A red circle, the number 42, and a blue square are arranged on a white background."
+  ],
+  "x2": [
+   " Red",
+   "42",
+   "A red circle, the number 42, and a blue square are displayed on a white background."
+  ]
+ },
+ "correct": {
+  "single": true,
+  "same24": true,
+  "x2": true
+ }
+}

bench/results/2026-09-29-layer-split/README.md

@@ -0,0 +1,84 @@
+# Layer split across GPUs (2026-09-29)
+
+**Rig (a community member's PC, "RIBPC"):**
+- Ryzen 9 9950X3D, 62 GB DDR5, Windows 11, CUDA 13.1.
+- RTX 5080 16 GB (x16), RTX 3090 24 GB (x4 gen4, ~6 GB/s), RTX 2080 Ti 22 GB (x4 gen3, Turing sm_75; the
+  experimental `STRATA_EXPERIMENTAL_SM75` build).
+
+**Model:** the Coder (GSQ-RCO IQ1_M, 48 layers x 256 experts = 12,288 expert pairs, ~23 GB of experts), 32K
+context, int8 KV, `--prefill auto`, `--spec 4`. It is the only model that fits the rig's RAM and disk.
+
+**Tools:** `rib_pp.py` (needle prompts at 2.7K/8K/16K/28K tokens with a code word at 50% depth, a 2-turn chat that
+must reuse its checkpoint, greedy decode of a story and a code prompt) and `rib_norepeat.py` (the Phase A
+no-repeat and sanity cases). Raw results are in `data/`.
+
+## Correctness
+
+| Check | Result |
+|---|---|
+| This branch vs the 0.1.20 release, one GPU (5080), fixed cache, all 10 cases | **10/10 byte-identical** |
+| This branch, one GPU vs the split on the same GPU (K=24, `--split-device 0`) | **10/10 byte-identical**: the hand-off is exact |
+| 5080 + 3090 (auto) and 5080 + 2080 Ti + 3090 (auto): no-repeat under presence 100 (greedy and sampled), 144 sanity | all pass, 0 repeats |
+| Needles at 2.7K-28K tokens, every configuration | all found |
+| 2-turn chat (the checkpoint restored on every GPU) | reused 6,631-6,632 of 6,660 tokens, answer right |
+
+Across GPUs the text is not byte-identical to one GPU: experts the CPU computed on one card run on a GPU in the split,
+and they round differently (the same effect as `--expert-cache`, bench/results/2026-09-27-cache-parity).
+
+## Speed
+
+**Prompt tok/s** at 16K / 28K tokens, and **decode tok/s** for story / code (greedy; three repeats averaged
+in the K sweep):
+
+| Configuration | Split | Prompt 16K | Prompt 28K | Decode story | Decode code | Decode hits |
+|---|---|---|---|---|---|---|
+| 0.1.20, 5080 alone | - | 2,045 | 2,005 | 83.2 | 88.2 | 70-84% |
+| this branch, 5080 alone | - | 2,017 | 1,974 | 83.1 | 88.0 | 70-84% |
+| this branch, 5080 alone, 3 repeats (adaptive swaps learn the prompt) | - | 1,726 | 1,970 | 86.7 | 105.2 | 91-92% |
+| 3090 alone | - | 1,253 | 1,211 | 71.7 | 92.9 | 86-93% |
+| 5080 + 3090 | K=18 | 1,547 | 1,694 | 77.2 | 103.8 | 99.9% |
+| 5080 + 3090 | K=22 | 1,840 | 2,074 | 80.2 | 106.4 | 99.8% |
+| 5080 + 3090 | K=24 | 1,978 | 2,258 | 83.5 | 109.5 | 99.5% |
+| **5080 + 3090** | **K=26** | **2,039** | **2,357** | **83.8** | **109.7** | 99.3% |
+| 5080 + 3090 | K=28 | 2,011 | 2,287 | 83.5 | 112.5 | 99.0% |
+| 5080 + 3090 | K=30 | 1,935 | 2,218 | 81.1 | 109.6 | 98% |
+| 5080 + 3090 | K=32 | 1,818 | 2,063 | 83.0 | 108.7 | 98% |
+| 5080 + 3090 | auto (K=22) | 2,037 | 2,073 | 79.5 | 108.9 | 99.7% |
+| 3090 + 5080 | auto (K=30) | 1,672 | 1,876 | 90.3 | 105.1 | 99.4% |
+| 5080 + 2080 Ti + 3090 | auto (22, 23) | 1,687 | 1,847 | 67.6 | 89.6 | 99.7% |
+| 5080 + 3090 + 2080 Ti | first auto (12, 33) | 1,148 | 1,144 | 51.9 | 69.7 | 100% |
+| 5080 + 2080 Ti | first auto | 914 | 906 | 45.5 | 58.0 | 97% |
+
+What decides it:
+
+- **The best two-GPU split for the Coder is K=26-28.** Prompts run +18-20% over the 5080 alone at 16-28K;
+  decode is on par for story and +4-7% for code.
+- **Residency saturates quickly: the per-layer GPU speed decides.** From K=18 up, both caches hold 98-100% of
+  the routed experts. Moving layers to the faster card is what helps: the 3090 costs 0.50 ms per layer per
+  window, the 5080 0.33 (`STRATA_SPLIT_TIMING`, the "wait for the GPU" per stage).
+- **Decode is bounded by that GPU time.** One 5080 with its cache adapted spends 16.3 ms waiting for its GPU and
+  5.5 ms in the CPU pool per window. The split removes the pool (0.8-1.0 ms) but adds the slower card's layers:
+  7.9 + 12.1 ms at K=24. The per-layer GPU half (kernels plus the host round trip that publishes each layer's
+  expert plan) is the next thing to cut, for one GPU as well (perf-review-plan E-6).
+- **A third, slower card costs more than it holds.** The 2080 Ti's one-layer stage took 3.1 ms per window.
+  For a model that already fits two cards, leave it out. It pays only when the two faster cards cannot hold most
+  of the routed experts (a bigger model; not testable on this rig's 62 GB of RAM).
+- **Prompt chunk:** 1024 instead of 2048 frees ~0.7 GB per card, but prompts read 7-12% slower.
+
+## Auto placement
+
+`--layer-split auto` predicts one decode window's time for every placement (every placement up to three GPUs) and
+keeps the fastest:
+
+- **per-layer time** from SMs x clock (0.33 ms for an RTX 5080);
+- **cache contents:** each card's layers' profiled pairs, hottest first, as the fill does;
+- **routed mass** of rank r taken as (r+1)^-1.2 (fits the sweep's hit rates within 0.1-1%);
+- **missed mass** costing 190 ms per unit (fitted to the sweep's best K; `STRATA_SPLIT_MISS_MS` overrides).
+
+It picked K=22 on the 5080 + 3090: within 0-12% of the best fixed split on prompts and on par on decode. It gives
+a slow third card a single layer.
+
+## Reproduce
+
+On a rig: the `strata-remote` tools, then `rib_matrix.bat`, `rib_ksweep.bat`, `rib_validate.bat` (in the dev
+notes, not in this repository).

bench/results/2026-09-29-layer-split/data/norepeat-nr-v-x2-auto-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 88,
+  "drafts_offered": 193,
+  "tok_s": 74.6,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was seventy years old, but he moved with the grace of a man who had spent decades on a narrow spiral staircase. His hands, rough as sandpaper, gripped the iron railing as he ascended the final flight of steps to the lantern room.\n\nBelow him, the Atlantic churned in a frenzy, whitecaps exploding against the black rocks like fireworks. Above, the sky was a bruised purple, heavy with rain that hadn\u2019t yet fallen.\n\nElias checked the clock. 11:42 PM. The light was due.\n\nHe didn\u2019t flip a switch. He didn\u2019t press a button. He reached for the heavy brass lever that had worn smooth by his palm over the years. With a grunt that matched the strain of his aging muscles, he pulled it down.\n\n*Clunk.*\n\nThe"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 136,
+  "drafts_offered": 181,
+  "tok_s": 105.5,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 85.8,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 94.3,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 118,
+  "repeats": 0,
+  "drafts_accepted": 37,
+  "drafts_offered": 105,
+  "tok_s": 67.9,
+  "text": "Aardvark  \nAlbatross   \nAlligator    \nAntelope     \nBaboon       \nBadger      \nBeaver        \nBear          \nBird of Paradise \nBuffalo         \nCamel           \nCheetah            \nChimpanzee             \nCrane              \nCrocodile                \nDeer                 \nDolphin               \nDonkey                  \nElephant                   \nFlamingo                    \nFox                       \nGiraffe                     \nGoat                      \nHippopotamus  \nIguana       \nJaguar        \nKangaroo      \nKoala          \nLion         \nLeopard     \nMonkey    \nMoose   \nOstrich \nOtter\nPanda<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 147,
+  "repeats": 0,
+  "drafts_accepted": 26,
+  "drafts_offered": 103,
+  "tok_s": 63.2,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty cathedral hall outside my window at midnight on November third this year\u2014so I pulled up to that date and time for context because you asked me about a lighthouse keeper but gave no specifics beyond \u201cshort story,\u201d so let\u2019s set it: isolated coastal station off the Oregon coast during winter storm season, 1987.\n\nMy name is Elias Vane (I made this fictional; real keepers often kept journals signed with initials only), and I\u2019m writing from memory because my logbook got waterlogged when a rogue wave breached lower storage room at dawn\u2014so here\u2019s what happened:<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 109,
+  "repeats": 0,
+  "drafts_accepted": 13,
+  "drafts_offered": 56,
+  "tok_s": 54.1,
+  "text": "The wind didn\u2019t just blow at Cape Hollow; it screamed through the gaps in my cottage\u2019s shutters, rattling them like loose teeth until they settled into silence with every storm break out of three hundred days here being storms that broke something else again but mostly kept me warm because I burned coal and wood whenever we had any left over from last winter when even then if you\u2019re lucky enough to get through it all without freezing yourself so hard your own thoughts become ice too\n\nBut Elias knew better than anyone: fear was useful only until dawn<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 92,
+  "repeats": 0,
+  "drafts_accepted": 26,
+  "drafts_offered": 48,
+  "tok_s": 64.7,
+  "text": "Lion  \nTiger   \nElephant \nGiraffe    \nZebra     \nPanda       \nKoala      \nKangaroo        \nHippopotamus          \nRhinoceros            \nCamel              \nCheetah             \nLeopard           \nPanther         \nJaguar                \nBison               \nElk                 \nDeer                  \nFox                   \nWolf                    \nBear                     \nLlama                       \nDonkey                        \nGoat                      \nSheep                         \nCow                           \nPig                          \nRabbit                            \nCat                              \nDog<|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 14,
+  "tok_s": 71.7,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 53,
+  "drafts_offered": 134,
+  "tok_s": 66.1,
+  "text": "The ocean is not merely water; it has been, and continues to be one with humanity\u2019s most profound narrative arc in human civilization: **the story we tell ourselves through our relationship** between landmasses separated by vast expansiveness that defines both isolation from other worlds (and thus their own unique evolutionary paths) as well than connection across them via currents wind patterns tides depth pressure temperature salinity biodiversity geology climate change economic trade routes ecological systems cultural exchange political boundaries scientific discovery technological advancement environmental degradation conservation efforts maritime archaeography historical cartographic evolution legal frameworks international law enforcement mechanisms insurance liability regimes regulatory compliance standards safety protocols navigation aids communication networks emergency response strategies search-and-rescue operations salvage rights ownership disputes heritage protection zones sustainable harvesting practices aquaculture development infrastructure engineering projects coastal management policies urban planning regulations zoning ordinances building codes architectural design guidelines aesthetic considerations functional requirements accessibility provisions energy efficiency measures thermal insulation techniques moisture control methods ventilation optimization lighting solutions acoustic soundproofing structural integrity assessments seismic resistance evaluations flood mitigation plans storm surge barriers levee construction seawall reinforcement breakwater installation harbor dredging channel maintenance buoy placement lighthouse automation radar monitoring sonar mapping bathymetric surveys hydrographic charts nautical almanacs tide tables current predictions weather forecasts marine meteorological models satellite imagery remote sensing data assimilation numerical simulations computational fluid dynamics finite element analysis partial differential equations tensor calculus linear algebra probability theory statistics stochastic processes Markov chains Bayesian inference machine learning artificial neural network deep convolutional recurrent transformer attention heads generative adversarial diffusion transformers large language model tokenization"
+ }
+]

bench/results/2026-09-29-layer-split/data/norepeat-nr-v-x3-auto-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 88,
+  "drafts_offered": 193,
+  "tok_s": 68.2,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was seventy years old, but he moved with the grace of a man who had spent decades on a narrow spiral staircase. His hands, rough as sandpaper, gripped the iron railing as he ascended the final flight of steps to the lantern room.\n\nBelow him, the Atlantic churned in a frenzy, whitecaps exploding against the black rocks like fireworks. Above, the sky was a bruised purple, heavy with rain that hadn\u2019t yet fallen.\n\nElias checked the clock. 11:42 PM. The light was due.\n\nHe didn\u2019t flip a switch. He didn\u2019t press a button. He reached for the heavy brass lever that had worn smooth by his palm over the years. With a grunt that matched the strain of his aging muscles, he pulled it down.\n\n*Clunk.*\n\nThe"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 136,
+  "drafts_offered": 181,
+  "tok_s": 99.4,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 74.5,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 76.3,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 118,
+  "repeats": 0,
+  "drafts_accepted": 37,
+  "drafts_offered": 105,
+  "tok_s": 65.2,
+  "text": "Aardvark  \nAlbatross   \nAlligator    \nAntelope     \nBaboon       \nBadger      \nBeaver        \nBear          \nBird of Paradise \nBuffalo         \nCamel           \nCheetah            \nChimpanzee             \nCrane              \nCrocodile                \nDeer                 \nDolphin               \nDonkey                  \nElephant                   \nFlamingo                    \nFox                       \nGiraffe                     \nGoat                      \nHippopotamus  \nIguana       \nJaguar        \nKangaroo      \nKoala          \nLion         \nLeopard     \nMonkey    \nMoose   \nOstrich \nOtter\nPanda<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 147,
+  "repeats": 0,
+  "drafts_accepted": 26,
+  "drafts_offered": 103,
+  "tok_s": 45.7,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty cathedral hall outside my window at midnight on November third this year\u2014so I pulled up to that date and time for context because you asked me about a lighthouse keeper but gave no specifics beyond \u201cshort story,\u201d so let\u2019s set it: isolated coastal station off the Oregon coast during winter storm season, 1987.\n\nMy name is Elias Vane (I made this fictional; real keepers often kept journals signed with initials only), and I\u2019m writing from memory because my logbook got waterlogged when a rogue wave breached lower storage room at dawn\u2014so here\u2019s what happened:<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 109,
+  "repeats": 0,
+  "drafts_accepted": 13,
+  "drafts_offered": 56,
+  "tok_s": 42.1,
+  "text": "The wind didn\u2019t just blow at Cape Hollow; it screamed through the gaps in my cottage\u2019s shutters, rattling them like loose teeth until they settled into silence with every storm break out of three hundred days here being storms that broke something else again but mostly kept me warm because I burned coal and wood whenever we had any left over from last winter when even then if you\u2019re lucky enough to get through it all without freezing yourself so hard your own thoughts become ice too\n\nBut Elias knew better than anyone: fear was useful only until dawn<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 92,
+  "repeats": 0,
+  "drafts_accepted": 26,
+  "drafts_offered": 48,
+  "tok_s": 43.9,
+  "text": "Lion  \nTiger   \nElephant \nGiraffe    \nZebra     \nPanda       \nKoala      \nKangaroo        \nHippopotamus          \nRhinoceros            \nCamel              \nCheetah             \nLeopard           \nPanther         \nJaguar                \nBison               \nElk                 \nDeer                  \nFox                   \nWolf                    \nBear                     \nLlama                       \nDonkey                        \nGoat                      \nSheep                         \nCow                           \nPig                          \nRabbit                            \nCat                              \nDog<|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 14,
+  "tok_s": 61.4,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 53,
+  "drafts_offered": 134,
+  "tok_s": 51.9,
+  "text": "The ocean is not merely water; it has been, and continues to be one with humanity\u2019s most profound narrative arc in human civilization: **the story we tell ourselves through our relationship** between landmasses separated by vast expansiveness that defines both isolation from other worlds (and thus their own unique evolutionary paths) as well than connection across them via currents wind patterns tides depth pressure temperature salinity biodiversity geology climate change economic trade routes ecological systems cultural exchange political boundaries scientific discovery technological advancement environmental degradation conservation efforts maritime archaeography historical cartographic evolution legal frameworks international law enforcement mechanisms insurance liability regimes regulatory compliance standards safety protocols navigation aids communication networks emergency response strategies search-and-rescue operations salvage rights ownership disputes heritage protection zones sustainable harvesting practices aquaculture development infrastructure engineering projects coastal management policies urban planning regulations zoning ordinances building codes architectural design guidelines aesthetic considerations functional requirements accessibility provisions energy efficiency measures thermal insulation techniques moisture control methods ventilation optimization lighting solutions acoustic soundproofing structural integrity assessments seismic resistance evaluations flood mitigation plans storm surge barriers levee construction seawall reinforcement breakwater installation harbor dredging channel maintenance buoy placement lighthouse automation radar monitoring sonar mapping bathymetric surveys hydrographic charts nautical almanacs tide tables current predictions weather forecasts marine meteorological models satellite imagery remote sensing data assimilation numerical simulations computational fluid dynamics finite element analysis partial differential equations tensor calculus linear algebra probability theory statistics stochastic processes Markov chains Bayesian inference machine learning artificial neural network deep convolutional recurrent transformer attention heads generative adversarial diffusion transformers large language model tokenization"
+ }
+]

bench/results/2026-09-29-layer-split/data/norepeat-nr-x2-auto-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 91,
+  "drafts_offered": 190,
+  "tok_s": 74.0,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was seventy years old, but he moved with the grace of a man who had spent decades on a narrow spiral staircase. His hands, rough as sandpaper, knew every bolt, every lever, and every creak in the iron bones of the tower.\n\nFor forty years, Elias had been the guardian of the Point. Not just of the light, but of the silence between the waves.\n\nIt was November. The sky was a bruised purple, heavy with rain that hadn\u2019t yet fallen. The sea was a churning cauldron of grey and white, throwing itself against the granite base with a violence that shook the floorboards beneath Elias\u2019s boots.\n\nHe climbed the stairs. One hundred and twelve steps. He counted them by feel, his left hand trailing along the cold iron railing. At the top, the air was"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 137,
+  "drafts_offered": 178,
+  "tok_s": 103.4,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 91.1,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 70.7,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 118,
+  "repeats": 0,
+  "drafts_accepted": 38,
+  "drafts_offered": 108,
+  "tok_s": 65.4,
+  "text": "Aardvark  \nAlbatross   \nAlligator    \nAntelope     \nBaboon       \nBadger      \nBeaver        \nBear          \nBird of Paradise \nBuffalo         \nCamel           \nCheetah            \nChimpanzee             \nCrane              \nCrocodile                \nDeer                 \nDolphin               \nDonkey                  \nElephant                   \nFlamingo                    \nFox                       \nGiraffe                     \nGoat                      \nHippopotamus  \nIguana       \nJaguar        \nKangaroo      \nKoala          \nLion         \nLeopard     \nMonkey    \nMoose   \nOstrich \nOtter\nPanda<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 57,
+  "repeats": 0,
+  "drafts_accepted": 11,
+  "drafts_offered": 61,
+  "tok_s": 57.1,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty cathedral vaults below Elias\u2019s boots were heavy with salt and exhaustion as he climbed one hundred twelve steps to reach top room where his world began again.<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 58,
+  "repeats": 0,
+  "drafts_accepted": 14,
+  "drafts_offered": 54,
+  "tok_s": 52.9,
+  "text": "The wind didn\u2019t just blow at Cape Harrow; it screamed through the gaps in stone and steel, carrying with them spray from three miles out into churning black water that no longer resembled an ocean so much as abyssal chaos waiting for its prey to surface beneath waves of salt.<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 59,
+  "repeats": 0,
+  "drafts_accepted": 11,
+  "drafts_offered": 47,
+  "tok_s": 51.7,
+  "text": "Lion  \nTiger  \n\nElephant\\nGiraffe\\Zebra\\rHippopotamus\\tRhinoceros\\vCrocodile\\fAlligator\\bSnake\\aSpider\\u2615CoffeeCup\u2615\ufe0fTeaTime\ud83d\udc09DragonFishWhaleDolph<|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 12,
+  "tok_s": 73.5,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 43,
+  "drafts_offered": 126,
+  "tok_s": 63.4,
+  "text": "The ocean is not merely water; it has been, and continues to be one with humanity\u2019s most profound narrative arc in human civilization: **the story told by waves**. It serves as both witness (through sedimentary layers)and participant( through currents that carry messages across continents). Its \"history\" spans geological epochs where life first emerged from primordial pools into complex ecosystems today\u2014and cultural histories shaped entirely around its roleas connector between distant lands or barrier separating them forever depending on perspective taken at different times throughout millennia since ancient civilizations began building boats outof logs carved using stone tools until modern container ships carrying billions tons cargo daily cross Atlantic routes once navigated onlyby stars alone under moonlight during nights when sailors feared monsters lurking beneath hulls made fragile against storms they could barely predict even now despite advanced meteorology systems developed over past century after industrial revolution transformed maritime trade patterns globally due economic pressures driving demand for faster logistics chains linking factories producing electronics manufactured inside cities located far inland near rivers feeding estuaries opening directly onto open seas connected via canals engineered centuries ago like Suez Canal built originallyfor military purposes later adapted commercial use post-World War II era reshaping global supply networks dramatically because geopolitical shifts altered which ports remained accessible politically versus physically blocked temporarily then reopened permanently following treaty agreements signed among nations agreeing upon shared responsibilities regarding environmental stewardship including coral reef restoration efforts funded jointly international organizations coordinating scientific research conducted aboard vessels specifically designed deep-sea exploration equipped robotic submersibles capable descending trenches deeper than any previous technology allowed"
+ }
+]

bench/results/2026-09-29-layer-split/data/norepeat-nr-x3-auto-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 98,
+  "drafts_offered": 166,
+  "tok_s": 54.4,
+  "text": "The wind didn\u2019t just blow; it screamed. It tore through the iron gallery of the Blackwood Point Lighthouse, rattling the glass panes like a prisoner shaking its bars.\n\nElias Thorne was seventy years old, and he had been the keeper for forty of them. He knew every creak in the spiral staircase, every draft that slipped under the door, and every shift in the weather that the barometer couldn\u2019t quite predict. He knew that when the fog rolled in thick enough to swallow the horizon, the world ceased to exist. There was only the light, the stone, and him.\n\nIt was November, the month of storms. The sea was a churning cauldron of grey and white, throwing itself against the granite base with a violence that made the floorboards tremble. Elias stood by the lantern room, his hands wrapped around a mug of coffee that had gone cold hours ago. He wasn\u2019t drinking it. He was holding it for warmth."
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 137,
+  "drafts_offered": 163,
+  "tok_s": 70.7,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv(file_path: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys being the header values\n    and values being the corresponding cell values.\n    \n    Args:\n        file_path: Path to the CSV file.\n        \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result = []\n    with open(file_path, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_basic():\n    \"\"\"Test basic CSV parsing with simple data.\"\"\"\n    import tempfile\n    import os\n    \n    # Create a temporary CSV"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 56.7,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 57.6,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 59,
+  "repeats": 0,
+  "drafts_accepted": 13,
+  "drafts_offered": 47,
+  "tok_s": 39.7,
+  "text": "Aardvark  \nAlbatross  \n\nAlligator   \nAntelope    \nBaboon      \nBadger     \nBeaver       \nBear        \nBird         \nBuffalo     \n\nCat          \nCheetah      \n\nChimpanzee \nClam         \n\n\nCrocodile   \n\n\n\nDolphin      \n\n\n\n\nDonkey       <|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 57,
+  "repeats": 0,
+  "drafts_accepted": 12,
+  "drafts_offered": 58,
+  "tok_s": 39.9,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty cathedral vaults below Elias\u2019s boots were heavy with salt and exhaustion as he climbed one hundred twelve steps to reach topmost gallery where his world began.<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 30,
+  "drafts_offered": 111,
+  "tok_s": 34.7,
+  "text": "The wind didn\u2019t just blow at Blackwood Rock; it screamed through the gaps in his stone cottage like an angry ghost trying to get inside, yet finding no door left unlocked because Elias never let one stay that way for more than three seconds after entering or leaving during storm season. He had been doing this since 1987\u2014since before he even knew why\u2014and now it was muscle memory so deep into his bones and fingers\u2019 calloused skin texture patterns worn thin by years of gripping the same iron railing at midnight watch that if you asked him what time exactly, down to quarter-hour increments when fog rolled in thick enough where light beams bent around itself like old rope coiling tight on a winch drum spooling out slowly from below deck floor level storage locker number seven under stairs leading"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 96,
+  "repeats": 0,
+  "drafts_accepted": 31,
+  "drafts_offered": 48,
+  "tok_s": 42.3,
+  "text": "Lion  \nTiger   \nElephant \nGiraffe    \nZebra     \nPanda       \nKoala      \nKangaroo        \nCheetah         \nHippopotamus          \nRhinoceros            \nLeopard             \nJaguar              \nWolf                \nFox                 \nBear                  \nDeer                    \nOtter                   \nBeaver                      \nBadger                        \nMongoose                          \nMeerkat                           \nChimpanzee                            \nGorilla                             \nOrangetutan                              \nAntelope                                \nBison                                   \nElk                                     <|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 13,
+  "tok_s": 43.0,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 29,
+  "drafts_offered": 127,
+  "tok_s": 37.6,
+  "text": "The ocean is not merely water; it has been, and remains to this day one giant machine for making life possible on Earth.\u201d \u2014 *David Attenborough* \n\nThis quote captures perhaps more than any other single sentence in human language: that which we call \u201cthe Sea\u201d or \"Ocean\" (terms often used interchangeably but distinct geographically) was never just an element within our planet\u2019s geography\u2014it became its engine itself\u2014a living system whose existence predates humanity by billions years yet continues shaping us today through climate regulation oxygen production food supply trade routes cultural identity ecological resilience economic development political boundaries scientific discovery technological innovation environmental crisis conservation efforts historical memory philosophical reflection poetic metaphor musical composition cinematic storytelling literary narrative visual art architectural inspiration culinary tradition spiritual symbolism psychological influence sociological transformation educational foundation medical necessity agricultural dependency industrial revolution urban planning infrastructural engineering legal framework regulatory policy international cooperation global governance planetary stewardship existential risk mitigation sustainable practice ethical consideration moral imperative social justice democratic participation civic engagement public health community welfare individual responsibility personal accountability collective action shared experience common understanding mutual respect reciprocal trust collaborative effort cooperative endeavor joint venture unified mission integrated strategy coordinated plan synchronized schedule aligned timeline concurrent execution simultaneous operation parallel processing sequential progression iterative refinement recursive improvement continuous adaptation dynamic adjustment flexible response adaptive behavior responsive conduct proactive initiative anticipatory foresight predictive modeling probabilistic assessment statistical analysis empirical observation experimental verification theoretical hypothesis conceptual abstraction logical deduction rational inference critical evaluation analytical reasoning systematic investigation methodical inquiry structured exploration comprehensive examination detailed scrutiny meticulous inspection thorough review exhaustive audit complete survey full census total enumeration absolute"
+ }
+]

bench/results/2026-09-29-layer-split/data/norepeat-reg-dev-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 88,
+  "drafts_offered": 187,
+  "tok_s": 59.2,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was seventy years old, but he moved with the grace of a man who had spent decades on a narrow spiral staircase. His hands, mapped with veins like the roots of an ancient oak, gripped the cold iron railing.\n\nFor forty years, Elias had tended the light at the end of the world. Not the end of the map, but the end of the land. Here, the Atlantic threw itself against the granite cliffs with such violence that the spray reached the gallery, thirty feet above the rocks.\n\nHe checked the clock. 11:42 PM. The fog was thickening, a gray soup that swallowed the horizon. In the old days, he would have climbed the stairs to the lantern room, polished the Fresnel lens, and wound the clockwork mechanism that turned the great beam. But the automation had changed"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 135,
+  "drafts_offered": 179,
+  "tok_s": 81.6,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 74.9,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 74.3,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 61,
+  "repeats": 0,
+  "drafts_accepted": 19,
+  "drafts_offered": 49,
+  "tok_s": 49.6,
+  "text": "Aardvark  \nAlbatross  \n\nAlligator   \nAntelope    \nBaboon      \nBadger     \nBeaver       \nBear        \nBird         \nBoar          \nBuffalo \nButterfly \n\nCamel           \nCat            \nCheetah        \n\nDolphin         \n\n\nElephant        \n\n\n\nFlamingo<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 80,
+  "repeats": 0,
+  "drafts_accepted": 6,
+  "drafts_offered": 52,
+  "tok_s": 44.9,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty cathedral hall outside my window at midnight on November third this year\u2014so I pulled up to check what was happening with that storm and why they were calling me out there when all we had left for tonight\u2019s shift is one last pass through our logs before dawn breaks.<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 17,
+  "drafts_offered": 83,
+  "tok_s": 44.1,
+  "text": "The wind didn\u2019t just blow at Cape Harrow; it screamed through the gaps in its teeth, hungry and relentless for three centuries of stone salt-spray history that had long since forgotten to be polite or gentle with itself against anything smaller than God Himself was willing acknowledge as divine protection from drowning souls who were already lost before they ever touched water.\n\nElias knew this rhythm better he himself could hear it sometimes; his boots worn smooth by pacing the spiral stair\u2019s center-post groove where thousands upon countless steps had rubbed away texture until all that remained beneath sole leather now felt like polished bone carved out slowly but surely over time into something more hollow than wood ever really should be allowed become when used so often enough within such confined circular spaces meant only for vertical ascent down always descending again back upward never truly leaving"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 62,
+  "repeats": 0,
+  "drafts_accepted": 18,
+  "drafts_offered": 31,
+  "tok_s": 49.5,
+  "text": "Lion  \nTiger  \n\nElephant  \n  \nGiraffe  \n\n\n\nHippopotamus    \nZebra   \nRhinoceros   \n\n\nPanda Bear    \n\n\n\n\nKangaroo     \nKoala      \nSloth      \n\n\n\n\n\nCheetah       \nLeopard        \nPanther        \n\n\n\n\n\n\nWolf              \nFox                \nBear                 <|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 13,
+  "tok_s": 65.2,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 47,
+  "drafts_offered": 153,
+  "tok_s": 52.5,
+  "text": "The ocean is not merely water; it has been, and remains to this day one giant machine for making life possible on Earth.\" \u2014 *David Attenborough* \n\nThis quote captures perhaps more than any other single sentence in human language: that which we call \"the Sea\" or \u201cOcean\u201d was never just an element within our planet\u2019s geography but rather its most fundamental biological engine\u2014a living system whose existence predates humanity by billions years yet continues shaping every aspect from climate regulation through evolutionary biology all way down modern industrial supply chains today's global shipping lanes carry cargo across vast distances because they were once crossed only slowly via coastal hopping routes used since antiquity until steamships revolutionized travel during late nineteenth century when diesel engines replaced wind power entirely allowing container ships carrying thousands TEUs (Twenty-foot Equivalent Units) per voyage crossing entire Pacific basins without stopping at intermediate ports anymore unlike earlier sailing vessels needing favorable winds currents seasonal patterns dictating departure windows based upon monsoon calendars established centuries ago before technological advances changed those constraints fundamentally altering logistics networks worldwide thereby transforming economic structures globally while simultaneously creating ecological disruptions due invasive species transported unintentionally alongside legitimate goods causing cascading ecosystem collapses locally where non-native organisms outcompete native fauna disrupting food webs leading population declines affecting biodiversity indices measured scientifically using standardized metrics like Shannon-Wiener diversity index calculations applied consistently over decades revealing trends showing significant decreases post-introduction events correl strongly with introduction dates matching historical records documenting first sightings confirmed taxonomically classified formally according International Code Nomenclature rules"
+ }
+]

bench/results/2026-09-29-layer-split/data/norepeat-reg-rel-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 88,
+  "drafts_offered": 187,
+  "tok_s": 58.4,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was seventy years old, but he moved with the grace of a man who had spent decades on a narrow spiral staircase. His hands, mapped with veins like the roots of an ancient oak, gripped the cold iron railing.\n\nFor forty years, Elias had tended the light at the end of the world. Not the end of the map, but the end of the land. Here, the Atlantic threw itself against the granite cliffs with such violence that the spray reached the gallery, thirty feet above the rocks.\n\nHe checked the clock. 11:42 PM. The fog was thickening, a gray soup that swallowed the horizon. In the old days, he would have climbed the stairs to the lantern room, polished the Fresnel lens, and wound the clockwork mechanism that turned the great beam. But the automation had changed"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 135,
+  "drafts_offered": 179,
+  "tok_s": 80.6,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 75.2,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 74.2,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 61,
+  "repeats": 0,
+  "drafts_accepted": 19,
+  "drafts_offered": 49,
+  "tok_s": 48.5,
+  "text": "Aardvark  \nAlbatross  \n\nAlligator   \nAntelope    \nBaboon      \nBadger     \nBeaver       \nBear        \nBird         \nBoar          \nBuffalo \nButterfly \n\nCamel           \nCat            \nCheetah        \n\nDolphin         \n\n\nElephant        \n\n\n\nFlamingo<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 80,
+  "repeats": 0,
+  "drafts_accepted": 6,
+  "drafts_offered": 52,
+  "tok_s": 46.4,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty cathedral hall outside my window at midnight on November third this year\u2014so I pulled up to check what was happening with that storm and why they were calling me out there when all we had left for tonight\u2019s shift is one last pass through our logs before dawn breaks.<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 17,
+  "drafts_offered": 83,
+  "tok_s": 43.3,
+  "text": "The wind didn\u2019t just blow at Cape Harrow; it screamed through the gaps in its teeth, hungry and relentless for three centuries of stone salt-spray history that had long since forgotten to be polite or gentle with itself against anything smaller than God Himself was willing acknowledge as divine protection from drowning souls who were already lost before they ever touched water.\n\nElias knew this rhythm better he himself could hear it sometimes; his boots worn smooth by pacing the spiral stair\u2019s center-post groove where thousands upon countless steps had rubbed away texture until all that remained beneath sole leather now felt like polished bone carved out slowly but surely over time into something more hollow than wood ever really should be allowed become when used so often enough within such confined circular spaces meant only for vertical ascent down always descending again back upward never truly leaving"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 62,
+  "repeats": 0,
+  "drafts_accepted": 18,
+  "drafts_offered": 31,
+  "tok_s": 49.8,
+  "text": "Lion  \nTiger  \n\nElephant  \n  \nGiraffe  \n\n\n\nHippopotamus    \nZebra   \nRhinoceros   \n\n\nPanda Bear    \n\n\n\n\nKangaroo     \nKoala      \nSloth      \n\n\n\n\n\nCheetah       \nLeopard        \nPanther        \n\n\n\n\n\n\nWolf              \nFox                \nBear                 <|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 13,
+  "tok_s": 62.5,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 47,
+  "drafts_offered": 153,
+  "tok_s": 52.6,
+  "text": "The ocean is not merely water; it has been, and remains to this day one giant machine for making life possible on Earth.\" \u2014 *David Attenborough* \n\nThis quote captures perhaps more than any other single sentence in human language: that which we call \"the Sea\" or \u201cOcean\u201d was never just an element within our planet\u2019s geography but rather its most fundamental biological engine\u2014a living system whose existence predates humanity by billions years yet continues shaping every aspect from climate regulation through evolutionary biology all way down modern industrial supply chains today's global shipping lanes carry cargo across vast distances because they were once crossed only slowly via coastal hopping routes used since antiquity until steamships revolutionized travel during late nineteenth century when diesel engines replaced wind power entirely allowing container ships carrying thousands TEUs (Twenty-foot Equivalent Units) per voyage crossing entire Pacific basins without stopping at intermediate ports anymore unlike earlier sailing vessels needing favorable winds currents seasonal patterns dictating departure windows based upon monsoon calendars established centuries ago before technological advances changed those constraints fundamentally altering logistics networks worldwide thereby transforming economic structures globally while simultaneously creating ecological disruptions due invasive species transported unintentionally alongside legitimate goods causing cascading ecosystem collapses locally where non-native organisms outcompete native fauna disrupting food webs leading population declines affecting biodiversity indices measured scientifically using standardized metrics like Shannon-Wiener diversity index calculations applied consistently over decades revealing trends showing significant decreases post-introduction events correl strongly with introduction dates matching historical records documenting first sightings confirmed taxonomically classified formally according International Code Nomenclature rules"
+ }
+]

bench/results/2026-09-29-layer-split/data/norepeat-reg-same24-coder-iq1_m.json

@@ -0,0 +1,92 @@
+[
+ {
+  "name": "greedy story 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 88,
+  "drafts_offered": 187,
+  "tok_s": 58.4,
+  "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was seventy years old, but he moved with the grace of a man who had spent decades on a narrow spiral staircase. His hands, mapped with veins like the roots of an ancient oak, gripped the cold iron railing.\n\nFor forty years, Elias had tended the light at the end of the world. Not the end of the map, but the end of the land. Here, the Atlantic threw itself against the granite cliffs with such violence that the spray reached the gallery, thirty feet above the rocks.\n\nHe checked the clock. 11:42 PM. The fog was thickening, a gray soup that swallowed the horizon. In the old days, he would have climbed the stairs to the lantern room, polished the Fresnel lens, and wound the clockwork mechanism that turned the great beam. But the automation had changed"
+ },
+ {
+  "name": "greedy code 200",
+  "tokens": 200,
+  "repeats": 0,
+  "drafts_accepted": 135,
+  "drafts_offered": 179,
+  "tok_s": 80.5,
+  "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+ },
+ {
+  "name": "greedy sanity",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 74.5,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy, no penalty (sanity)",
+  "tokens": 4,
+  "repeats": 0,
+  "drafts_accepted": 3,
+  "drafts_offered": 3,
+  "tok_s": 76.8,
+  "text": "144<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64",
+  "tokens": 61,
+  "repeats": 0,
+  "drafts_accepted": 19,
+  "drafts_offered": 49,
+  "tok_s": 49.6,
+  "text": "Aardvark  \nAlbatross  \n\nAlligator   \nAntelope    \nBaboon      \nBadger     \nBeaver       \nBear        \nBird         \nBoar          \nBuffalo \nButterfly \n\nCamel           \nCat            \nCheetah        \n\nDolphin         \n\n\nElephant        \n\n\n\nFlamingo<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=64 story",
+  "tokens": 80,
+  "repeats": 0,
+  "drafts_accepted": 6,
+  "drafts_offered": 52,
+  "tok_s": 46.7,
+  "text": "The wind didn\u2019t just blow; it screamed against the glass of Lantern House 42, rattling like chains in an empty cathedral hall outside my window at midnight on November third this year\u2014so I pulled up to check what was happening with that storm and why they were calling me out there when all we had left for tonight\u2019s shift is one last pass through our logs before dawn breaks.<|im_end|>"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 3",
+  "tokens": 160,
+  "repeats": 0,
+  "drafts_accepted": 17,
+  "drafts_offered": 83,
+  "tok_s": 44.3,
+  "text": "The wind didn\u2019t just blow at Cape Harrow; it screamed through the gaps in its teeth, hungry and relentless for three centuries of stone salt-spray history that had long since forgotten to be polite or gentle with itself against anything smaller than God Himself was willing acknowledge as divine protection from drowning souls who were already lost before they ever touched water.\n\nElias knew this rhythm better he himself could hear it sometimes; his boots worn smooth by pacing the spiral stair\u2019s center-post groove where thousands upon countless steps had rubbed away texture until all that remained beneath sole leather now felt like polished bone carved out slowly but surely over time into something more hollow than wood ever really should be allowed become when used so often enough within such confined circular spaces meant only for vertical ascent down always descending again back upward never truly leaving"
+ },
+ {
+  "name": "sampled presence=100 last_n=64 seed 11",
+  "tokens": 62,
+  "repeats": 0,
+  "drafts_accepted": 18,
+  "drafts_offered": 31,
+  "tok_s": 50.0,
+  "text": "Lion  \nTiger  \n\nElephant  \n  \nGiraffe  \n\n\n\nHippopotamus    \nZebra   \nRhinoceros   \n\n\nPanda Bear    \n\n\n\n\nKangaroo     \nKoala      \nSloth      \n\n\n\n\n\nCheetah       \nLeopard        \nPanther        \n\n\n\n\n\n\nWolf              \nFox                \nBear                 <|im_end|>"
+ },
+ {
+  "name": "greedy frequency=100 last_n=16",
+  "tokens": 11,
+  "repeats": 0,
+  "drafts_accepted": 5,
+  "drafts_offered": 13,
+  "tok_s": 62.0,
+  "text": "1 to 50, separated by commas:<|im_end|>"
+ },
+ {
+  "name": "greedy presence=100 last_n=4096 (8-row windows)",
+  "tokens": 300,
+  "repeats": 0,
+  "drafts_accepted": 47,
+  "drafts_offered": 153,
+  "tok_s": 52.1,
+  "text": "The ocean is not merely water; it has been, and remains to this day one giant machine for making life possible on Earth.\" \u2014 *David Attenborough* \n\nThis quote captures perhaps more than any other single sentence in human language: that which we call \"the Sea\" or \u201cOcean\u201d was never just an element within our planet\u2019s geography but rather its most fundamental biological engine\u2014a living system whose existence predates humanity by billions years yet continues shaping every aspect from climate regulation through evolutionary biology all way down modern industrial supply chains today's global shipping lanes carry cargo across vast distances because they were once crossed only slowly via coastal hopping routes used since antiquity until steamships revolutionized travel during late nineteenth century when diesel engines replaced wind power entirely allowing container ships carrying thousands TEUs (Twenty-foot Equivalent Units) per voyage crossing entire Pacific basins without stopping at intermediate ports anymore unlike earlier sailing vessels needing favorable winds currents seasonal patterns dictating departure windows based upon monsoon calendars established centuries ago before technological advances changed those constraints fundamentally altering logistics networks worldwide thereby transforming economic structures globally while simultaneously creating ecological disruptions due invasive species transported unintentionally alongside legitimate goods causing cascading ecosystem collapses locally where non-native organisms outcompete native fauna disrupting food webs leading population declines affecting biodiversity indices measured scientifically using standardized metrics like Shannon-Wiener diversity index calculations applied consistently over decades revealing trends showing significant decreases post-introduction events correl strongly with introduction dates matching historical records documenting first sightings confirmed taxonomically classified formally according International Code Nomenclature rules"
+ }
+]

bench/results/2026-09-29-layer-split/data/pp-dev-3090.json

@@ -0,0 +1,72 @@
+{
+ "label": "dev-3090",
+ "extra": [],
+ "gpus": "2",
+ "needles": [
+  {
+   "tokens": 2726,
+   "prompt_ms": 3424.8,
+   "pp_tok_s": 796.0,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 8379,
+   "prompt_ms": 8617.9,
+   "pp_tok_s": 972.3,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 16066,
+   "prompt_ms": 12820.1,
+   "pp_tok_s": 1253.2,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 22901.1,
+   "pp_tok_s": 1211.4,
+   "found": true,
+   "answer": "willow-474<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 5657.8,
+  "turn2_tokens": 6660,
+  "reused": 6631,
+  "turn2_ms": 238.7,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 71.7,
+   "hit_rate": 0.9266798230257504,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias had lived in the tower for thirty years, and he knew the difference between a gale and a hurricane by the way the glass rattled in its frame. Tonight, it was the latter. The sea was a churning black void, punctuated by whitecaps that looked like teeth.\n\nHe climbed the spiral stairs, his knees protesting with every step. The iron rungs were cold, slick with condensation that had leaked through the hairline cracks in the masonry. At the top, the lantern room hummed with the low, steady thrum of the rotating lens. It was a sound Elias had learned to sleep with, a heartbeat of the house.\n\nHe checked the clock. 11:42 PM. The light swept across the water, a slow, hypnotic arc. *Flash. Darkness. Flash. Darkness.*\n\nFor a moment, the beam caught something that wasn\u2019t water. A shape"
+  },
+  {
+   "name": "code",
+   "tok_s": 92.9,
+   "hit_rate": 0.8636411400016346,
+   "text": "```python\nimport csv\nfrom typing import List, Dict\n\n\ndef parse_csv(filepath: str) -> List[Dict[str, str]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header row\n    and values from the corresponding row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result = []\n    with open(filepath, 'r', newline='') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n```<|im_end|>"
+  }
+ ],
+ "engine_lines": [
+  "strata generate: expert cache auto: 17.31 GiB free, 700 MiB reserved -> 6704 slots",
+  "strata generate: expert cache 8730 slots, 16.62 GiB of VRAM; policy is",
+  "strata serve: the prompt path borrows 2315 cache slots (4.42 GiB)",
+  "strata serve: decode expert cache hit rate: 86.6% (4986 hits / 5756 lookups)",
+  "strata serve: decode expert cache hit rate: 87.1% (3757 hits / 4315 lookups)",
+  "strata serve: decode expert cache hit rate: 88.7% (3827 hits / 4314 lookups)",
+  "strata serve: decode expert cache hit rate: 92.1% (3975 hits / 4318 lookups)",
+  "strata serve: decode expert cache hit rate: 95.5% (4124 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 94.3% (25793 hits / 27360 lookups)",
+  "strata serve: decode expert cache hit rate: 94.6% (4088 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 92.7% (116454 hits / 125668 lookups)",
+  "strata serve: decode expert cache hit rate: 86.4% (73970 hits / 85649 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-dev-5080.json

@@ -0,0 +1,72 @@
+{
+ "label": "dev-5080",
+ "extra": [],
+ "gpus": "0",
+ "needles": [
+  {
+   "tokens": 2726,
+   "prompt_ms": 2129.8,
+   "pp_tok_s": 1279.9,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 8379,
+   "prompt_ms": 5057.2,
+   "pp_tok_s": 1656.8,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 16066,
+   "prompt_ms": 7964.7,
+   "pp_tok_s": 2017.2,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 14053.6,
+   "pp_tok_s": 1974.1,
+   "found": true,
+   "answer": "willow-474<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3366.4,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 197.3,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 83.1,
+   "hit_rate": 0.8418683557684931,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias had lived in the tower for thirty years, and he knew the difference between a gale and a hurricane by the way the glass rattled in its frame. Tonight, it was the latter. The sea was a churning cauldron of black ink and white foam, throwing itself against the granite base with the force of a battering ram.\n\nInside the lantern room, the air was thick with the smell of kerosene and old brass. Elias wiped his hands on his woolen trousers, leaving faint, oily smears on the fabric. He checked the clock. 11:42 PM. The rotation was due.\n\nHe reached for the crank handle, a heavy iron wheel worn smooth by decades of his own palms. With a grunt that matched the strain of his shoulders, he began to turn it. *Click. Click. Click.* The gears engaged, and the massive Fresnel lens began its slow"
+  },
+  {
+   "name": "code",
+   "tok_s": 88.0,
+   "hit_rate": 0.7011385968111186,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "engine_lines": [
+  "strata generate: expert cache auto: 9.15 GiB free, 700 MiB reserved -> 3415 slots",
+  "strata generate: expert cache 4293 slots, 8.17 GiB of VRAM; policy is",
+  "strata serve: the prompt path borrows 2343 cache slots (4.42 GiB)",
+  "strata serve: decode expert cache hit rate: 59.6% (2749 hits / 4610 lookups)",
+  "strata serve: decode expert cache hit rate: 64.2% (2136 hits / 3329 lookups)",
+  "strata serve: decode expert cache hit rate: 67.3% (2309 hits / 3432 lookups)",
+  "strata serve: decode expert cache hit rate: 72.5% (2539 hits / 3504 lookups)",
+  "strata serve: decode expert cache hit rate: 77.3% (2817 hits / 3642 lookups)",
+  "strata serve: decode expert cache hit rate: 75.3% (16500 hits / 21916 lookups)",
+  "strata serve: decode expert cache hit rate: 80.0% (2978 hits / 3723 lookups)",
+  "strata serve: decode expert cache hit rate: 84.2% (98752 hits / 117301 lookups)",
+  "strata serve: decode expert cache hit rate: 70.1% (69215 hits / 98718 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-ks-k18.json

@@ -0,0 +1,85 @@
+{
+ "label": "ks-k18",
+ "extra": [
+  "--layer-split",
+  "18"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 10383.7,
+   "pp_tok_s": 1547.2,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 16371.9,
+   "pp_tok_s": 1694.5,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 4308.0,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 239.8,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 77.2,
+   "reps": [
+    74.6,
+    78.1,
+    79.0
+   ],
+   "hit_rate": 0.9985378787878788,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias had lived in the tower for thirty years, and he knew the difference between a gale and a hurricane by the way the glass rattled in its frame. Tonight, the glass was vibrating like a plucked cello string. The sea, usually a rhythmic pulse against the granite base, was now a chaotic, frothing beast, throwing itself against the rocks with the force of a battering ram.\n\nElias climbed the spiral stairs, his hand gripping the cold iron railing. His knees ached, not from age, but from the constant vibration of the floor beneath his feet. He reached the lantern room, the heart of the lighthouse, and checked the clockwork mechanism. The great lens, a prism of Fresnel glass, rotated with a steady, hypnotic *whirrr-click, whirrr-click*. It was the only sound that mattered. The light swept out into the black void, cutting through"
+  },
+  {
+   "name": "code",
+   "tok_s": 103.8,
+   "reps": [
+    97.6,
+    106.4,
+    107.3
+   ],
+   "hit_rate": 0.9984863945578232,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 524 windows; per window: wait for the GPU 6.456 ms, pool + plan 0.181 ms, host staging 0.581 ms, commit 0.206 ms",
+  "strata serve: stage 1: 524 windows; per window: wait for the GPU 14.872 ms, pool + plan 0.501 ms, host staging 0.000 ms, commit 0.387 ms",
+  "strata serve: stage 0: 593 windows; per window: wait for the GPU 6.479 ms, pool + plan 0.185 ms, host staging 0.515 ms, commit 0.207 ms",
+  "strata serve: stage 1: 593 windows; per window: wait for the GPU 15.053 ms, pool + plan 0.496 ms, host staging 0.000 ms, commit 0.390 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 18)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4608 slots, 8.24 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 18-47, expert cache 7152 slots (14.14 GiB), 7152 of its 7680 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-17",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-17 (CUDA0), 18-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 98.7% (6159 hits / 6240 lookups)",
+  "strata serve: decode expert cache hit rate: 98.9% (3796 hits / 3840 lookups)",
+  "strata serve: decode expert cache hit rate: 99.2% (3811 hits / 3840 lookups)",
+  "strata serve: decode expert cache hit rate: 99.6% (27723 hits / 27840 lookups)",
+  "strata serve: decode expert cache hit rate: 99.1% (3807 hits / 3840 lookups)",
+  "strata serve: decode expert cache hit rate: 99.3% (142002 hits / 143040 lookups)",
+  "strata serve: decode expert cache hit rate: 99.8% (139882 hits / 140160 lookups)",
+  "strata serve: decode expert cache hit rate: 99.9% (131807 hits / 132000 lookups)",
+  "strata serve: decode expert cache hit rate: 99.0% (119278 hits / 120480 lookups)",
+  "strata serve: decode expert cache hit rate: 99.8% (117410 hits / 117600 lookups)",
+  "strata serve: decode expert cache hit rate: 99.8% (117422 hits / 117600 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-ks-k19.json

@@ -0,0 +1,85 @@
+{
+ "label": "ks-k19",
+ "extra": [
+  "--layer-split",
+  "19"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 9875.2,
+   "pp_tok_s": 1626.9,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 15498.0,
+   "pp_tok_s": 1790.1,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 4085.5,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 238.7,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 79.3,
+   "reps": [
+    74.8,
+    85.6,
+    77.4
+   ],
+   "hit_rate": 0.9977757017660928,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias had lived in the tower for thirty years, and he knew the difference between a gale and a hurricane by the way the glass rattled in its frame. Tonight, the glass was vibrating like a plucked cello string. The sea, usually a rhythmic pulse against the granite base, was now a chaotic, frothing beast, throwing itself against the rocks with the force of a battering ram.\n\nElias stood at the top of the spiral staircase, his hand resting on the cold iron railing. He was not afraid. Fear was for the tourists who came in summer, wide-eyed and clutching their cameras. Elias was a keeper. He was a guardian.\n\nHe checked the logbook. The entry for the night was simple: *Wind, 60 knots. Visibility, zero. Light, operational.*\n\nHe walked down the stairs, his boots heavy on the metal grating. The smell of salt"
+  },
+  {
+   "name": "code",
+   "tok_s": 107.4,
+   "reps": [
+    98.9,
+    111.3,
+    112.1
+   ],
+   "hit_rate": 0.9986286196529353,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header row\n    and values from the corresponding row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 533 windows; per window: wait for the GPU 6.226 ms, pool + plan 0.294 ms, host staging 0.561 ms, commit 0.225 ms",
+  "strata serve: stage 1: 533 windows; per window: wait for the GPU 14.156 ms, pool + plan 0.373 ms, host staging 0.000 ms, commit 0.371 ms",
+  "strata serve: stage 0: 599 windows; per window: wait for the GPU 6.314 ms, pool + plan 0.292 ms, host staging 0.501 ms, commit 0.225 ms",
+  "strata serve: stage 1: 599 windows; per window: wait for the GPU 14.366 ms, pool + plan 0.375 ms, host staging 0.000 ms, commit 0.374 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 19)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4606 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 19-47, expert cache 7160 slots (14.14 GiB), 7160 of its 7424 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-18",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-18 (CUDA0), 19-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 98.5% (6141 hits / 6234 lookups)",
+  "strata serve: decode expert cache hit rate: 99.0% (3797 hits / 3836 lookups)",
+  "strata serve: decode expert cache hit rate: 99.4% (3814 hits / 3837 lookups)",
+  "strata serve: decode expert cache hit rate: 99.5% (28659 hits / 28795 lookups)",
+  "strata serve: decode expert cache hit rate: 99.3% (3814 hits / 3839 lookups)",
+  "strata serve: decode expert cache hit rate: 99.2% (141378 hits / 142508 lookups)",
+  "strata serve: decode expert cache hit rate: 99.8% (124963 hits / 125273 lookups)",
+  "strata serve: decode expert cache hit rate: 99.8% (134574 hits / 134874 lookups)",
+  "strata serve: decode expert cache hit rate: 99.0% (121132 hits / 122322 lookups)",
+  "strata serve: decode expert cache hit rate: 99.9% (114073 hits / 114235 lookups)",
+  "strata serve: decode expert cache hit rate: 99.9% (113598 hits / 113754 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-ks-k20.json

@@ -0,0 +1,85 @@
+{
+ "label": "ks-k20",
+ "extra": [
+  "--layer-split",
+  "20"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 9044.3,
+   "pp_tok_s": 1776.4,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 13928.7,
+   "pp_tok_s": 1991.8,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3743.5,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 236.8,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 76.4,
+   "reps": [
+    74.2,
+    78.4,
+    76.7
+   ],
+   "hit_rate": 0.9979911611088791,
+   "text": "The wind didn\u2019t just blow; it screamed. It clawed at the granite base of the tower, trying to pry it from the bedrock, and it howled through the narrow slits of the lantern room glass.\n\nElias Thorne was seventy years old, but he moved with the grace of a man who had spent fifty years listening to the sea. He knew the rhythm of the waves against the rocks below\u2014the *thud, thud, crash*\u2014and he knew when that rhythm changed. When the sea grew too quiet, or too violent, he knew a storm was coming, or a ship was in trouble.\n\nTonight, the storm was a Category 4. The rain lashed against the windows like gravel thrown by a giant. Elias stood in the center of the lantern room, his hand resting on the cold brass railing. He wasn\u2019t afraid. He was a guardian.\n\nHe checked the clockwork mechanism. It was old, a relic from 1"
+  },
+  {
+   "name": "code",
+   "tok_s": 105.9,
+   "reps": [
+    103.2,
+    106.8,
+    107.7
+   ],
+   "hit_rate": 0.9981849807154201,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 537 windows; per window: wait for the GPU 6.685 ms, pool + plan 0.403 ms, host staging 0.593 ms, commit 0.215 ms",
+  "strata serve: stage 1: 537 windows; per window: wait for the GPU 13.928 ms, pool + plan 0.282 ms, host staging 0.000 ms, commit 0.359 ms",
+  "strata serve: stage 0: 606 windows; per window: wait for the GPU 6.764 ms, pool + plan 0.399 ms, host staging 0.528 ms, commit 0.216 ms",
+  "strata serve: stage 1: 606 windows; per window: wait for the GPU 14.108 ms, pool + plan 0.288 ms, host staging 0.000 ms, commit 0.362 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 20)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4603 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 20-47, expert cache 7142 slots (14.14 GiB), 7142 of its 7168 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-19",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-19 (CUDA0), 20-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 98.9% (6162 hits / 6230 lookups)",
+  "strata serve: decode expert cache hit rate: 99.2% (3803 hits / 3835 lookups)",
+  "strata serve: decode expert cache hit rate: 99.3% (3810 hits / 3836 lookups)",
+  "strata serve: decode expert cache hit rate: 99.5% (27185 hits / 27330 lookups)",
+  "strata serve: decode expert cache hit rate: 99.3% (3807 hits / 3835 lookups)",
+  "strata serve: decode expert cache hit rate: 99.2% (139825 hits / 140938 lookups)",
+  "strata serve: decode expert cache hit rate: 99.7% (142122 hits / 142524 lookups)",
+  "strata serve: decode expert cache hit rate: 99.8% (146556 hits / 146851 lookups)",
+  "strata serve: decode expert cache hit rate: 99.0% (118026 hits / 119233 lookups)",
+  "strata serve: decode expert cache hit rate: 99.8% (118729 hits / 118997 lookups)",
+  "strata serve: decode expert cache hit rate: 99.8% (118791 hits / 119007 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-ks-k21.json

@@ -0,0 +1,85 @@
+{
+ "label": "ks-k21",
+ "extra": [
+  "--layer-split",
+  "21"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 8880.5,
+   "pp_tok_s": 1809.1,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 13654.6,
+   "pp_tok_s": 2031.8,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3680.6,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 235.4,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 77.4,
+   "reps": [
+    80.2,
+    80.8,
+    71.2
+   ],
+   "hit_rate": 0.9973622550922132,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his woolen collar up to his chin, the rough fabric scratching against his stubble. Outside the thick, salt-crusted glass of the lantern room, the Atlantic was a churning cauldron of black and white foam. Rain lashed against the panes in horizontal sheets, blurring the world into a smear of gray and shadow.\n\nInside, however, it was warm. The smell of kerosene and old wood hung heavy in the air, a scent that had defined his life for thirty years.\n\nElias was not a man of many words. He was a man of many tasks. His hands, mapped with scars from rope burns and broken glass, moved with a rhythm that predated his memory. He checked the clockwork mechanism of the Fresnel lens, ensuring the rotation was smooth, silent, and steady. *Tick. Tick. Tick.* The sound was the heartbeat of the coast.\n\n"
+  },
+  {
+   "name": "code",
+   "tok_s": 106.7,
+   "reps": [
+    100.6,
+    110.5,
+    109.0
+   ],
+   "hit_rate": 0.998218711927068,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 527 windows; per window: wait for the GPU 6.934 ms, pool + plan 0.620 ms, host staging 0.530 ms, commit 0.245 ms",
+  "strata serve: stage 1: 527 windows; per window: wait for the GPU 13.912 ms, pool + plan 0.365 ms, host staging 0.000 ms, commit 0.359 ms",
+  "strata serve: stage 0: 595 windows; per window: wait for the GPU 7.031 ms, pool + plan 0.595 ms, host staging 0.472 ms, commit 0.245 ms",
+  "strata serve: stage 1: 595 windows; per window: wait for the GPU 14.051 ms, pool + plan 0.361 ms, host staging 0.000 ms, commit 0.361 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 21)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4627 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 21-47, expert cache 6912 slots (13.78 GiB), 6912 of its 6912 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-20",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-20 (CUDA0), 21-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 98.7% (5672 hits / 5748 lookups)",
+  "strata serve: decode expert cache hit rate: 99.4% (4287 hits / 4314 lookups)",
+  "strata serve: decode expert cache hit rate: 99.4% (4287 hits / 4315 lookups)",
+  "strata serve: decode expert cache hit rate: 99.3% (29024 hits / 29229 lookups)",
+  "strata serve: decode expert cache hit rate: 99.1% (4278 hits / 4316 lookups)",
+  "strata serve: decode expert cache hit rate: 98.8% (131499 hits / 133085 lookups)",
+  "strata serve: decode expert cache hit rate: 99.6% (130974 hits / 131451 lookups)",
+  "strata serve: decode expert cache hit rate: 99.7% (138767 hits / 139134 lookups)",
+  "strata serve: decode expert cache hit rate: 98.8% (121454 hits / 122932 lookups)",
+  "strata serve: decode expert cache hit rate: 99.8% (116809 hits / 117079 lookups)",
+  "strata serve: decode expert cache hit rate: 99.8% (118803 hits / 119015 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-ks-k22.json

@@ -0,0 +1,85 @@
+{
+ "label": "ks-k22",
+ "extra": [
+  "--layer-split",
+  "22"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 8730.9,
+   "pp_tok_s": 1840.1,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 13375.4,
+   "pp_tok_s": 2074.2,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3611.4,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 234.8,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 80.2,
+   "reps": [
+    78.4,
+    80.9,
+    81.5
+   ],
+   "hit_rate": 0.9977764197412695,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was seventy-three years old, and he had been the keeper of the Blackwood Point Light for forty of those years. The other thirty-three had been spent in a small, drafty cottage on the mainland, waiting for the day when the sea would finally claim him.\n\nTonight, the storm was a Category 4. The waves weren\u2019t just crashing; they were climbing. They reached the gallery railing, ten feet above the base of the tower, spraying a fine mist of brine that coated Elias\u2019s glasses.\n\nHe climbed the spiral stairs, his knees protesting with every step. The iron steps were cold, slick with condensation. At the top, in the lantern room, the air was thin and sharp. The great Fresnel lens, a cathedral of glass and brass, stood silent. It was time to wake it.\n\n"
+  },
+  {
+   "name": "code",
+   "tok_s": 106.4,
+   "reps": [
+    100.7,
+    110.3,
+    108.1
+   ],
+   "hit_rate": 0.9971798370756316,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 529 windows; per window: wait for the GPU 7.229 ms, pool + plan 0.561 ms, host staging 0.529 ms, commit 0.233 ms",
+  "strata serve: stage 1: 529 windows; per window: wait for the GPU 13.058 ms, pool + plan 0.253 ms, host staging 0.000 ms, commit 0.334 ms",
+  "strata serve: stage 0: 598 windows; per window: wait for the GPU 7.325 ms, pool + plan 0.552 ms, host staging 0.469 ms, commit 0.235 ms",
+  "strata serve: stage 1: 598 windows; per window: wait for the GPU 13.238 ms, pool + plan 0.260 ms, host staging 0.000 ms, commit 0.337 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 22)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4640 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 22-47, expert cache 6656 slots (13.34 GiB), 6656 of its 6656 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-21",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-21 (CUDA0), 22-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 97.7% (5609 hits / 5739 lookups)",
+  "strata serve: decode expert cache hit rate: 98.7% (4256 hits / 4310 lookups)",
+  "strata serve: decode expert cache hit rate: 99.1% (4278 hits / 4315 lookups)",
+  "strata serve: decode expert cache hit rate: 99.0% (27008 hits / 27289 lookups)",
+  "strata serve: decode expert cache hit rate: 98.8% (4260 hits / 4313 lookups)",
+  "strata serve: decode expert cache hit rate: 98.5% (135183 hits / 137274 lookups)",
+  "strata serve: decode expert cache hit rate: 99.6% (136132 hits / 136708 lookups)",
+  "strata serve: decode expert cache hit rate: 99.8% (135515 hits / 135817 lookups)",
+  "strata serve: decode expert cache hit rate: 98.4% (121287 hits / 123280 lookups)",
+  "strata serve: decode expert cache hit rate: 99.7% (117658 hits / 118026 lookups)",
+  "strata serve: decode expert cache hit rate: 99.7% (120574 hits / 120915 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-ks-k23.json

@@ -0,0 +1,85 @@
+{
+ "label": "ks-k23",
+ "extra": [
+  "--layer-split",
+  "23"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 8742.6,
+   "pp_tok_s": 1837.7,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 13084.2,
+   "pp_tok_s": 2120.3,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3566.1,
+  "turn2_tokens": 6660,
+  "reused": 6631,
+  "turn2_ms": 238.0,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 81.0,
+   "reps": [
+    76.8,
+    85.2,
+    81.1
+   ],
+   "hit_rate": 0.9961302681992337,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias had lived in the tower for thirty years, and he knew the difference between a gale and a hurricane by the way the glass rattled in its frame. Tonight, it was the latter. The sea was a churning black void, swallowing the horizon, throwing white foam against the granite base like a tantrum.\n\nInside the lantern room, the air was thick with the smell of kerosene and old brass. Elias wiped his hands on his wool trousers, the fabric stiff with salt and grease. He checked the clockwork mechanism that turned the lens. It was a beast of a thing, a Fresnel lens of eight feet in diameter, a cathedral of glass and crystal that focused the beam of the lamp into a single, piercing needle of light.\n\nHe wound the weights. *Click, click, click.* The gears engaged. The massive lens began its slow, hypnotic rotation.\n\nFor a moment, the"
+  },
+  {
+   "name": "code",
+   "tok_s": 108.4,
+   "reps": [
+    105.1,
+    109.0,
+    111.1
+   ],
+   "hit_rate": 0.9961698810290479,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 537 windows; per window: wait for the GPU 7.423 ms, pool + plan 0.953 ms, host staging 0.542 ms, commit 0.237 ms",
+  "strata serve: stage 1: 537 windows; per window: wait for the GPU 12.223 ms, pool + plan 0.236 ms, host staging 0.000 ms, commit 0.324 ms",
+  "strata serve: stage 0: 606 windows; per window: wait for the GPU 7.519 ms, pool + plan 0.904 ms, host staging 0.483 ms, commit 0.239 ms",
+  "strata serve: stage 1: 606 windows; per window: wait for the GPU 12.395 ms, pool + plan 0.242 ms, host staging 0.000 ms, commit 0.326 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 23)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4609 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 23-47, expert cache 6400 slots (12.82 GiB), 6400 of its 6400 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-22",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-22 (CUDA0), 23-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 96.8% (5528 hits / 5709 lookups)",
+  "strata serve: decode expert cache hit rate: 98.4% (4235 hits / 4303 lookups)",
+  "strata serve: decode expert cache hit rate: 98.9% (4260 hits / 4308 lookups)",
+  "strata serve: decode expert cache hit rate: 98.6% (30643 hits / 31089 lookups)",
+  "strata serve: decode expert cache hit rate: 98.6% (4248 hits / 4309 lookups)",
+  "strata serve: decode expert cache hit rate: 98.3% (134776 hits / 137143 lookups)",
+  "strata serve: decode expert cache hit rate: 99.4% (133024 hits / 133766 lookups)",
+  "strata serve: decode expert cache hit rate: 99.6% (129995 hits / 130500 lookups)",
+  "strata serve: decode expert cache hit rate: 97.9% (115782 hits / 118287 lookups)",
+  "strata serve: decode expert cache hit rate: 99.6% (117953 hits / 118464 lookups)",
+  "strata serve: decode expert cache hit rate: 99.6% (117560 hits / 118012 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-ks-k24.json

@@ -0,0 +1,85 @@
+{
+ "label": "ks-k24",
+ "extra": [
+  "--layer-split",
+  "24"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 8122.5,
+   "pp_tok_s": 1978.0,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 12285.8,
+   "pp_tok_s": 2258.1,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3407.0,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 234.0,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 83.5,
+   "reps": [
+    84.9,
+    83.3,
+    82.3
+   ],
+   "hit_rate": 0.9949381327334084,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his woolen collar up to his chin, the rough fabric scratching against his stubble. Outside the thick, salt-crusted glass of the lantern room, the Atlantic was a churning cauldron of black and white foam. Rain lashed against the panes in horizontal sheets, blurring the world into a smear of gray and shadow.\n\nInside, however, it was warm. The smell of kerosene and old wood hung heavy in the air, a scent that had defined Elias\u2019s life for thirty years. He was not merely a keeper; he was a guardian of silence.\n\nHe checked the clock. 11:42 PM. The rotation of the great Fresnel lens was due. With a practiced hand, he engaged the brake on the clockwork mechanism. The heavy brass gears groaned, then began their slow, rhythmic turn. *Tick. Tick. Tick.* It was a heartbeat"
+  },
+  {
+   "name": "code",
+   "tok_s": 109.5,
+   "reps": [
+    104.9,
+    111.0,
+    112.6
+   ],
+   "hit_rate": 0.9953796671318199,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 519 windows; per window: wait for the GPU 7.835 ms, pool + plan 0.767 ms, host staging 0.557 ms, commit 0.244 ms",
+  "strata serve: stage 1: 519 windows; per window: wait for the GPU 11.922 ms, pool + plan 0.232 ms, host staging 0.000 ms, commit 0.325 ms",
+  "strata serve: stage 0: 587 windows; per window: wait for the GPU 7.943 ms, pool + plan 0.744 ms, host staging 0.497 ms, commit 0.246 ms",
+  "strata serve: stage 1: 587 windows; per window: wait for the GPU 12.073 ms, pool + plan 0.238 ms, host staging 0.000 ms, commit 0.326 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 24)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4603 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 24-47, expert cache 6144 slots (12.35 GiB), 6144 of its 6144 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-23",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-23 (CUDA0), 24-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 95.9% (5916 hits / 6171 lookups)",
+  "strata serve: decode expert cache hit rate: 97.4% (3717 hits / 3815 lookups)",
+  "strata serve: decode expert cache hit rate: 98.4% (3761 hits / 3823 lookups)",
+  "strata serve: decode expert cache hit rate: 98.1% (27138 hits / 27664 lookups)",
+  "strata serve: decode expert cache hit rate: 97.8% (3742 hits / 3826 lookups)",
+  "strata serve: decode expert cache hit rate: 97.9% (126114 hits / 128875 lookups)",
+  "strata serve: decode expert cache hit rate: 99.2% (133626 hits / 134658 lookups)",
+  "strata serve: decode expert cache hit rate: 99.5% (132675 hits / 133350 lookups)",
+  "strata serve: decode expert cache hit rate: 96.8% (113593 hits / 117399 lookups)",
+  "strata serve: decode expert cache hit rate: 99.5% (118372 hits / 118949 lookups)",
+  "strata serve: decode expert cache hit rate: 99.5% (116981 hits / 117524 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-ks-k26.json

@@ -0,0 +1,85 @@
+{
+ "label": "ks-k26",
+ "extra": [
+  "--layer-split",
+  "26"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 7880.9,
+   "pp_tok_s": 2038.6,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 11771.9,
+   "pp_tok_s": 2356.7,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3323.9,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 231.5,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 83.8,
+   "reps": [
+    85.9,
+    83.1,
+    82.4
+   ],
+   "hit_rate": 0.9933966961830739,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his woolen collar up to his chin, the rough fabric scratching against his stubble. Outside the thick, salt-crusted glass of the lantern room, the Atlantic was a churning cauldron of black and white foam. Rain lashed against the panes in horizontal sheets, blurring the world into a smear of gray and green.\n\nInside, however, it was warm. The smell of kerosene and old wood hung heavy in the air, a scent that had defined Elias\u2019s life for thirty years. He was a keeper of the light, but more importantly, he was a keeper of time.\n\nHe checked his pocket watch. 11:42 PM. The rotation of the great Fresnel lens was due. With a practiced, rhythmic *clunk-clunk-clunk*, he wound the clockwork mechanism. The massive lens began its slow, hypnotic turn, sweeping its beam across"
+  },
+  {
+   "name": "code",
+   "tok_s": 109.7,
+   "reps": [
+    104.4,
+    112.7,
+    111.9
+   ],
+   "hit_rate": 0.9938670271352759,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 519 windows; per window: wait for the GPU 8.376 ms, pool + plan 1.030 ms, host staging 0.566 ms, commit 0.273 ms",
+  "strata serve: stage 1: 519 windows; per window: wait for the GPU 10.886 ms, pool + plan 0.214 ms, host staging 0.000 ms, commit 0.297 ms",
+  "strata serve: stage 0: 588 windows; per window: wait for the GPU 8.506 ms, pool + plan 0.985 ms, host staging 0.505 ms, commit 0.274 ms",
+  "strata serve: stage 1: 588 windows; per window: wait for the GPU 11.036 ms, pool + plan 0.219 ms, host staging 0.000 ms, commit 0.298 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 26)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4568 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 26-47, expert cache 5632 slots (11.32 GiB), 5632 of its 5632 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-25",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-25 (CUDA0), 26-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 92.8% (5259 hits / 5665 lookups)",
+  "strata serve: decode expert cache hit rate: 95.2% (4056 hits / 4259 lookups)",
+  "strata serve: decode expert cache hit rate: 97.2% (4164 hits / 4285 lookups)",
+  "strata serve: decode expert cache hit rate: 97.1% (27690 hits / 28510 lookups)",
+  "strata serve: decode expert cache hit rate: 97.5% (4184 hits / 4293 lookups)",
+  "strata serve: decode expert cache hit rate: 96.9% (121839 hits / 125724 lookups)",
+  "strata serve: decode expert cache hit rate: 98.9% (132165 hits / 133648 lookups)",
+  "strata serve: decode expert cache hit rate: 99.3% (137652 hits / 138567 lookups)",
+  "strata serve: decode expert cache hit rate: 95.3% (111307 hits / 116822 lookups)",
+  "strata serve: decode expert cache hit rate: 99.3% (118436 hits / 119329 lookups)",
+  "strata serve: decode expert cache hit rate: 99.4% (119109 hits / 119844 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-ks-k28.json

@@ -0,0 +1,85 @@
+{
+ "label": "ks-k28",
+ "extra": [
+  "--layer-split",
+  "28"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 7989.3,
+   "pp_tok_s": 2010.9,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 12132.9,
+   "pp_tok_s": 2286.6,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3433.5,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 228.0,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 83.5,
+   "reps": [
+    83.7,
+    82.4,
+    84.5
+   ],
+   "hit_rate": 0.9900441970361987,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias had lived in the tower for thirty years, and he knew the difference between a gale and a hurricane by the way the glass rattled in its frame. Tonight, the glass was vibrating like a plucked cello string. The sea, usually a rhythmic pulse against the granite base, was now a chaotic, frothing beast, throwing itself against the rocks with the force of a battering ram.\n\nElias climbed the spiral stairs, his hand gripping the cold iron railing. His knees ached, not from age, but from the constant vibration of the floor beneath his feet. He reached the lantern room, the heart of the lighthouse, and checked the clockwork mechanism. The great lens, a prism of Fresnel glass, rotated with a steady, hypnotic *whirrr-click, whirrr-click*. It was the only sound that mattered. The light swept out into the black void, cutting through"
+  },
+  {
+   "name": "code",
+   "tok_s": 112.5,
+   "reps": [
+    101.4,
+    112.1,
+    124.1
+   ],
+   "hit_rate": 0.9896636587366694,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv(file_path: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys being the header values\n    and values being the corresponding cell values.\n    \n    Args:\n        file_path: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result = []\n    with open(file_path, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n```<|im_end|>"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 527 windows; per window: wait for the GPU 8.765 ms, pool + plan 1.401 ms, host staging 0.593 ms, commit 0.281 ms",
+  "strata serve: stage 1: 527 windows; per window: wait for the GPU 9.893 ms, pool + plan 0.195 ms, host staging 0.000 ms, commit 0.276 ms",
+  "strata serve: stage 0: 578 windows; per window: wait for the GPU 8.908 ms, pool + plan 1.359 ms, host staging 0.559 ms, commit 0.284 ms",
+  "strata serve: stage 1: 578 windows; per window: wait for the GPU 10.025 ms, pool + plan 0.200 ms, host staging 0.000 ms, commit 0.278 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 28)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4537 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 28-47, expert cache 5120 slots (10.30 GiB), 5120 of its 5120 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-27",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-27 (CUDA0), 28-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 88.8% (5405 hits / 6086 lookups)",
+  "strata serve: decode expert cache hit rate: 93.8% (3539 hits / 3773 lookups)",
+  "strata serve: decode expert cache hit rate: 94.2% (3560 hits / 3781 lookups)",
+  "strata serve: decode expert cache hit rate: 95.7% (26702 hits / 27899 lookups)",
+  "strata serve: decode expert cache hit rate: 95.9% (3647 hits / 3804 lookups)",
+  "strata serve: decode expert cache hit rate: 95.7% (122618 hits / 128160 lookups)",
+  "strata serve: decode expert cache hit rate: 98.6% (135035 hits / 136884 lookups)",
+  "strata serve: decode expert cache hit rate: 99.0% (129476 hits / 130778 lookups)",
+  "strata serve: decode expert cache hit rate: 93.9% (111037 hits / 118290 lookups)",
+  "strata serve: decode expert cache hit rate: 98.9% (118829 hits / 120140 lookups)",
+  "strata serve: decode expert cache hit rate: 99.0% (90480 hits / 91425 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-ks-k30.json

@@ -0,0 +1,85 @@
+{
+ "label": "ks-k30",
+ "extra": [
+  "--layer-split",
+  "30"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 8301.3,
+   "pp_tok_s": 1935.4,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 12507.6,
+   "pp_tok_s": 2218.1,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3448.7,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 229.4,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 81.1,
+   "reps": [
+    78.0,
+    84.4,
+    81.0
+   ],
+   "hit_rate": 0.9798126997277784,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias had lived in the tower for thirty years, and he knew the difference between a gale and a hurricane by the way the glass rattled in its frame. Tonight, the glass was vibrating like a plucked cello string. The sea, usually a rhythmic pulse against the granite base, was now a chaotic, frothing beast, throwing itself against the rocks with the force of a battering ram.\n\nElias stood at the top of the spiral staircase, his hand resting on the cold iron railing. He was not afraid. Fear was for the tourists who came in summer, wide-eyed and clutching their cameras. Elias was a keeper. He was a guardian.\n\nHe checked the logbook. The entry for the night was simple: *Wind, 60 knots. Visibility, zero. Light, operational.*\n\nHe walked down the stairs, his boots heavy on the metal grating. The smell of salt"
+  },
+  {
+   "name": "code",
+   "tok_s": 109.6,
+   "reps": [
+    100.7,
+    114.1,
+    114.1
+   ],
+   "hit_rate": 0.9825370343977666,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 540 windows; per window: wait for the GPU 9.206 ms, pool + plan 1.794 ms, host staging 0.525 ms, commit 0.298 ms",
+  "strata serve: stage 1: 540 windows; per window: wait for the GPU 8.767 ms, pool + plan 0.173 ms, host staging 0.000 ms, commit 0.242 ms",
+  "strata serve: stage 0: 608 windows; per window: wait for the GPU 9.390 ms, pool + plan 1.733 ms, host staging 0.471 ms, commit 0.301 ms",
+  "strata serve: stage 1: 608 windows; per window: wait for the GPU 8.910 ms, pool + plan 0.178 ms, host staging 0.000 ms, commit 0.244 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 30)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4479 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 30-47, expert cache 4608 slots (9.19 GiB), 4608 of its 4608 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-29",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-29 (CUDA0), 30-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 84.6% (5099 hits / 6028 lookups)",
+  "strata serve: decode expert cache hit rate: 90.7% (3403 hits / 3751 lookups)",
+  "strata serve: decode expert cache hit rate: 91.1% (3415 hits / 3747 lookups)",
+  "strata serve: decode expert cache hit rate: 94.1% (26108 hits / 27737 lookups)",
+  "strata serve: decode expert cache hit rate: 93.4% (3534 hits / 3784 lookups)",
+  "strata serve: decode expert cache hit rate: 94.6% (127532 hits / 134866 lookups)",
+  "strata serve: decode expert cache hit rate: 98.6% (135828 hits / 137786 lookups)",
+  "strata serve: decode expert cache hit rate: 98.0% (132455 hits / 135184 lookups)",
+  "strata serve: decode expert cache hit rate: 91.0% (106351 hits / 116917 lookups)",
+  "strata serve: decode expert cache hit rate: 97.9% (115791 hits / 118246 lookups)",
+  "strata serve: decode expert cache hit rate: 98.3% (117198 hits / 119281 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-ks-k32.json

@@ -0,0 +1,85 @@
+{
+ "label": "ks-k32",
+ "extra": [
+  "--layer-split",
+  "32"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 8837.1,
+   "pp_tok_s": 1818.0,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 13449.8,
+   "pp_tok_s": 2062.7,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3565.7,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 227.0,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 83.0,
+   "reps": [
+    75.0,
+    86.1,
+    87.8
+   ],
+   "hit_rate": 0.9796934433020751,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias had lived in the tower for thirty years, and he knew the difference between a gale and a hurricane by the way the glass rattled in its frame. Tonight, it was the latter. The sea was a churning cauldron of black ink and white foam, throwing itself against the granite base with the force of a battering ram.\n\nInside the lantern room, the air was thick with the smell of kerosene and old brass. Elias wiped his hands on his woolen trousers, leaving faint, oily smears on the fabric. He checked the clock. 11:42 PM. The rotation was due.\n\nHe reached for the crank handle, a heavy iron wheel worn smooth by decades of his own palms. With a grunt that matched the strain of his shoulders, he began to turn it. *Click. Click. Click.* The gears engaged, and the massive Fresnel lens began its slow"
+  },
+  {
+   "name": "code",
+   "tok_s": 108.7,
+   "reps": [
+    98.8,
+    112.2,
+    115.1
+   ],
+   "hit_rate": 0.9777186846317358,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 533 windows; per window: wait for the GPU 9.839 ms, pool + plan 2.192 ms, host staging 0.585 ms, commit 0.318 ms",
+  "strata serve: stage 1: 533 windows; per window: wait for the GPU 8.014 ms, pool + plan 0.156 ms, host staging 0.000 ms, commit 0.231 ms",
+  "strata serve: stage 0: 602 windows; per window: wait for the GPU 10.014 ms, pool + plan 2.111 ms, host staging 0.520 ms, commit 0.321 ms",
+  "strata serve: stage 1: 602 windows; per window: wait for the GPU 8.094 ms, pool + plan 0.160 ms, host staging 0.000 ms, commit 0.232 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 32)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4488 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 32-47, expert cache 4096 slots (8.26 GiB), 4096 of its 4096 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-31",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-31 (CUDA0), 32-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 81.3% (4889 hits / 6010 lookups)",
+  "strata serve: decode expert cache hit rate: 87.7% (3272 hits / 3733 lookups)",
+  "strata serve: decode expert cache hit rate: 87.9% (3280 hits / 3733 lookups)",
+  "strata serve: decode expert cache hit rate: 92.3% (24238 hits / 26254 lookups)",
+  "strata serve: decode expert cache hit rate: 91.5% (3457 hits / 3778 lookups)",
+  "strata serve: decode expert cache hit rate: 93.7% (133254 hits / 142240 lookups)",
+  "strata serve: decode expert cache hit rate: 98.0% (130112 hits / 132812 lookups)",
+  "strata serve: decode expert cache hit rate: 98.0% (130069 hits / 132765 lookups)",
+  "strata serve: decode expert cache hit rate: 89.1% (105263 hits / 118190 lookups)",
+  "strata serve: decode expert cache hit rate: 97.2% (116970 hits / 120309 lookups)",
+  "strata serve: decode expert cache hit rate: 97.8% (115450 hits / 118081 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-ks-single.json

@@ -0,0 +1,76 @@
+{
+ "label": "ks-single",
+ "extra": [],
+ "gpus": "0",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 9310.4,
+   "pp_tok_s": 1725.6,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 14085.4,
+   "pp_tok_s": 1969.6,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3388.7,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 200.7,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 86.7,
+   "reps": [
+    78.2,
+    91.4,
+    90.4
+   ],
+   "hit_rate": 0.921882148773369,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was seventy-three years old, and his hands were a map of the coastline he had guarded for fifty years. The knuckles were swollen, the skin cracked like dry earth, but they moved with a precision that no machine could replicate.\n\nHe stood on the gallery of the *Harrow Point* lighthouse, the iron railing cold against his palms. Below, the Atlantic churned in a frenzy, whitecaps exploding against the black rocks like fireworks. Above, the sky was a bruised purple, heavy with rain that hadn\u2019t yet fallen.\n\nElias checked the clock. 11:42 PM. The light was due.\n\nHe didn\u2019t look at the gauge. He didn\u2019t check the fuel levels. He knew. He always knew. The rhythm of the ocean, the pressure of the air, the subtle vibration"
+  },
+  {
+   "name": "code",
+   "tok_s": 105.2,
+   "reps": [
+    87.8,
+    113.5,
+    114.2
+   ],
+   "hit_rate": 0.9109811738648947,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 382 windows; per window: wait for the GPU 15.155 ms, pool + plan 4.331 ms, host staging 0.656 ms, commit 0.458 ms",
+  "strata serve: stage 0: 455 windows; per window: wait for the GPU 15.790 ms, pool + plan 5.552 ms, host staging 0.688 ms, commit 0.467 ms",
+  "strata serve: stage 0: 524 windows; per window: wait for the GPU 16.064 ms, pool + plan 5.529 ms, host staging 0.606 ms, commit 0.472 ms",
+  "strata serve: stage 0: 593 windows; per window: wait for the GPU 16.305 ms, pool + plan 5.462 ms, host staging 0.540 ms, commit 0.475 ms"
+ ],
+ "engine_lines": [
+  "strata generate: expert cache auto: 9.15 GiB free, 700 MiB reserved -> 3415 slots",
+  "strata generate: expert cache 4293 slots, 8.17 GiB of VRAM; policy is",
+  "strata serve: the prompt path borrows 2343 cache slots (4.42 GiB)",
+  "strata serve: decode expert cache hit rate: 59.6% (2749 hits / 4610 lookups)",
+  "strata serve: decode expert cache hit rate: 67.8% (2299 hits / 3391 lookups)",
+  "strata serve: decode expert cache hit rate: 68.5% (2345 hits / 3424 lookups)",
+  "strata serve: decode expert cache hit rate: 75.6% (16605 hits / 21959 lookups)",
+  "strata serve: decode expert cache hit rate: 73.3% (2608 hits / 3558 lookups)",
+  "strata serve: decode expert cache hit rate: 83.7% (104878 hits / 125346 lookups)",
+  "strata serve: decode expert cache hit rate: 92.7% (119739 hits / 129184 lookups)",
+  "strata serve: decode expert cache hit rate: 92.2% (116867 hits / 126770 lookups)",
+  "strata serve: decode expert cache hit rate: 68.1% (64111 hits / 94116 lookups)",
+  "strata serve: decode expert cache hit rate: 89.0% (96370 hits / 108259 lookups)",
+  "strata serve: decode expert cache hit rate: 91.1% (102827 hits / 112875 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-rel-5080.json

@@ -0,0 +1,72 @@
+{
+ "label": "rel-5080",
+ "extra": [],
+ "gpus": "0",
+ "needles": [
+  {
+   "tokens": 2726,
+   "prompt_ms": 2132.8,
+   "pp_tok_s": 1278.1,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 8379,
+   "prompt_ms": 5008.9,
+   "pp_tok_s": 1672.8,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 16066,
+   "prompt_ms": 7855.4,
+   "pp_tok_s": 2045.2,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 13833.9,
+   "pp_tok_s": 2005.4,
+   "found": true,
+   "answer": "willow-474<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3298.2,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 197.9,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 83.2,
+   "hit_rate": 0.8418683557684931,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias had lived in the tower for thirty years, and he knew the difference between a gale and a hurricane by the way the glass rattled in its frame. Tonight, it was the latter. The sea was a churning cauldron of black ink and white foam, throwing itself against the granite base with the force of a battering ram.\n\nInside the lantern room, the air was thick with the smell of kerosene and old brass. Elias wiped his hands on his woolen trousers, leaving faint, oily smears on the fabric. He checked the clock. 11:42 PM. The rotation was due.\n\nHe reached for the crank handle, a heavy iron wheel worn smooth by decades of his own palms. With a grunt that matched the strain of his shoulders, he began to turn it. *Click. Click. Click.* The gears engaged, and the massive Fresnel lens began its slow"
+  },
+  {
+   "name": "code",
+   "tok_s": 88.2,
+   "hit_rate": 0.7011385968111186,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "engine_lines": [
+  "strata generate: expert cache auto: 9.15 GiB free, 700 MiB reserved -> 3415 slots",
+  "strata generate: expert cache 4293 slots, 8.17 GiB of VRAM; policy is",
+  "strata serve: the prompt path borrows 2343 cache slots (4.42 GiB)",
+  "strata serve: decode expert cache hit rate: 59.6% (2749 hits / 4610 lookups)",
+  "strata serve: decode expert cache hit rate: 64.2% (2136 hits / 3329 lookups)",
+  "strata serve: decode expert cache hit rate: 67.3% (2309 hits / 3432 lookups)",
+  "strata serve: decode expert cache hit rate: 72.5% (2539 hits / 3504 lookups)",
+  "strata serve: decode expert cache hit rate: 77.3% (2817 hits / 3642 lookups)",
+  "strata serve: decode expert cache hit rate: 75.3% (16500 hits / 21916 lookups)",
+  "strata serve: decode expert cache hit rate: 80.0% (2978 hits / 3723 lookups)",
+  "strata serve: decode expert cache hit rate: 84.2% (98752 hits / 117301 lookups)",
+  "strata serve: decode expert cache hit rate: 70.1% (69215 hits / 98718 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-t75-5080.json

@@ -0,0 +1,78 @@
+{
+ "label": "t75-5080",
+ "extra": [],
+ "gpus": "0",
+ "needles": [
+  {
+   "tokens": 2726,
+   "prompt_ms": 2158.8,
+   "pp_tok_s": 1262.7,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 8379,
+   "prompt_ms": 5060.0,
+   "pp_tok_s": 1655.9,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3389.7,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 213.5,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 80.4,
+   "reps": [
+    80.4
+   ],
+   "hit_rate": 0.855538332528651,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias had lived in the tower for thirty years, and he knew the difference between a gale and a hurricane by the way the glass rattled in its frame. Tonight, it was the latter. The sea was a churning black void, punctuated by whitecaps that looked like teeth.\n\nHe climbed the spiral stairs, his boots heavy with salt and exhaustion. The iron steps groaned under his weight, a sound that had become so familiar to him that he could sleep to it. But tonight, he wasn\u2019t sleeping. He was working.\n\nThe lens was the heart of the lighthouse. A massive, rotating Fresnel lens, a cathedral of glass and brass that turned with a mechanical hum. Elias checked the clockwork mechanism. It was smooth, rhythmic, a heartbeat in the dark. But the light itself was failing.\n\nHe climbed higher, into the lantern room. The wind battered the glass panes,"
+  },
+  {
+   "name": "code",
+   "tok_s": 87.5,
+   "reps": [
+    87.5
+   ],
+   "hit_rate": 0.7075461363025227,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 39 windows; per window: wait for the GPU 17.252 ms, pool + plan 8.473 ms, host staging 0.611 ms, commit 0.525 ms",
+  "strata serve: stage 0: 47 windows; per window: wait for the GPU 18.018 ms, pool + plan 8.616 ms, host staging 0.607 ms, commit 0.534 ms",
+  "strata serve: stage 0: 169 windows; per window: wait for the GPU 15.223 ms, pool + plan 5.717 ms, host staging 0.688 ms, commit 0.467 ms",
+  "strata serve: stage 0: 243 windows; per window: wait for the GPU 16.500 ms, pool + plan 7.316 ms, host staging 0.742 ms, commit 0.481 ms"
+ ],
+ "engine_lines": [
+  "strata generate: expert cache auto: 9.15 GiB free, 700 MiB reserved -> 3415 slots",
+  "strata generate: expert cache 4294 slots, 8.18 GiB of VRAM; policy is",
+  "strata serve: the prompt path borrows 2343 cache slots (4.42 GiB)",
+  "strata serve: decode expert cache hit rate: 59.6% (2749 hits / 4610 lookups)",
+  "strata serve: decode expert cache hit rate: 64.2% (2136 hits / 3329 lookups)",
+  "strata serve: decode expert cache hit rate: 67.3% (2309 hits / 3432 lookups)",
+  "strata serve: decode expert cache hit rate: 75.5% (16316 hits / 21602 lookups)",
+  "strata serve: decode expert cache hit rate: 74.4% (2660 hits / 3573 lookups)",
+  "strata serve: decode expert cache hit rate: 83.4% (92664 hits / 111086 lookups)",
+  "strata serve: decode expert cache hit rate: 72.0% (70946 hits / 98601 lookups)",
+  "strata generate: expert cache auto: 9.15 GiB free, 700 MiB reserved -> 3415 slots",
+  "strata generate: expert cache 4293 slots, 8.17 GiB of VRAM; policy is",
+  "strata serve: the prompt path borrows 2343 cache slots (4.42 GiB)",
+  "strata serve: decode expert cache hit rate: 59.6% (2749 hits / 4610 lookups)",
+  "strata serve: decode expert cache hit rate: 64.2% (2136 hits / 3329 lookups)",
+  "strata serve: decode expert cache hit rate: 67.3% (2309 hits / 3432 lookups)",
+  "strata serve: decode expert cache hit rate: 75.5% (16316 hits / 21602 lookups)",
+  "strata serve: decode expert cache hit rate: 74.4% (2659 hits / 3572 lookups)",
+  "strata serve: decode expert cache hit rate: 85.6% (101004 hits / 118059 lookups)",
+  "strata serve: decode expert cache hit rate: 70.8% (71044 hits / 100409 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-v-x2-auto.json

@@ -0,0 +1,103 @@
+{
+ "label": "v-x2-auto",
+ "extra": [
+  "--layer-split",
+  "auto"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 2726,
+   "prompt_ms": 2577.0,
+   "pp_tok_s": 1057.8,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 8379,
+   "prompt_ms": 4433.5,
+   "pp_tok_s": 1889.9,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 16066,
+   "prompt_ms": 7885.8,
+   "pp_tok_s": 2037.3,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 13384.6,
+   "pp_tok_s": 2072.8,
+   "found": true,
+   "answer": "willow-474<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3667.5,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 253.8,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 79.5,
+   "reps": [
+    78.9,
+    79.0,
+    80.7
+   ],
+   "hit_rate": 0.9969903443250137,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his woolen collar up to his chin, the rough fabric scratching against his stubble. Outside the thick, salt-crusted glass of the lantern room, the Atlantic was a churning cauldron of black and white foam. Rain lashed against the panes in horizontal sheets, blurring the world into a smear of gray and shadow.\n\nInside, however, it was warm. The smell of kerosene and old wood hung heavy in the air, a scent that had defined his life for thirty years.\n\nElias was not a man of many words. He was a man of many tasks. His hands, mapped with scars from rope burns and broken glass, moved with a rhythm that predated his memory. He checked the clockwork mechanism of the Fresnel lens, listening for the faint, rhythmic *tick-tick-tick* that signaled the rotation was true. If the rhythm faltered, ships"
+  },
+  {
+   "name": "code",
+   "tok_s": 108.9,
+   "reps": [
+    103.3,
+    113.7,
+    109.5
+   ],
+   "hit_rate": 0.9971795386830036,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 542 windows; per window: wait for the GPU 7.167 ms, pool + plan 0.572 ms, host staging 0.550 ms, commit 0.232 ms",
+  "strata serve: stage 1: 542 windows; per window: wait for the GPU 12.855 ms, pool + plan 0.250 ms, host staging 0.000 ms, commit 0.334 ms",
+  "strata serve: stage 0: 610 windows; per window: wait for the GPU 7.276 ms, pool + plan 0.559 ms, host staging 0.493 ms, commit 0.234 ms",
+  "strata serve: stage 1: 610 windows; per window: wait for the GPU 13.048 ms, pool + plan 0.258 ms, host staging 0.000 ms, commit 0.337 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split auto)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: layer split auto: CUDA0 84 SMs at 2.81 GHz -> 0.31 ms per layer, 8.30 GiB for experts",
+  "strata generate: layer split auto: CUDA1 82 SMs at 1.86 GHz -> 0.48 ms per layer, 14.14 GiB for experts",
+  "strata generate: layer split auto: K=22 - predicted 19.7 ms per decode window; the caches hold 11298 of 12288 profiled pairs (~99.7% of the routed mass)",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4640 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 22-47, expert cache 6656 slots (13.34 GiB), 6656 of its 6656 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-21",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-21 (CUDA0), 22-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 97.7% (5609 hits / 5739 lookups)",
+  "strata serve: decode expert cache hit rate: 98.5% (4241 hits / 4306 lookups)",
+  "strata serve: decode expert cache hit rate: 98.9% (4262 hits / 4309 lookups)",
+  "strata serve: decode expert cache hit rate: 99.4% (4290 hits / 4315 lookups)",
+  "strata serve: decode expert cache hit rate: 99.6% (4303 hits / 4319 lookups)",
+  "strata serve: decode expert cache hit rate: 98.8% (28379 hits / 28721 lookups)",
+  "strata serve: decode expert cache hit rate: 99.3% (4285 hits / 4314 lookups)",
+  "strata serve: decode expert cache hit rate: 98.5% (136232 hits / 138256 lookups)",
+  "strata serve: decode expert cache hit rate: 99.5% (135540 hits / 136216 lookups)",
+  "strata serve: decode expert cache hit rate: 99.7% (136812 hits / 137225 lookups)",
+  "strata serve: decode expert cache hit rate: 98.4% (118437 hits / 120406 lookups)",
+  "strata serve: decode expert cache hit rate: 99.7% (112836 hits / 113230 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-v-x2r-auto.json

@@ -0,0 +1,88 @@
+{
+ "label": "v-x2r-auto",
+ "extra": [
+  "--layer-split",
+  "auto"
+ ],
+ "gpus": "2,0",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 9610.0,
+   "pp_tok_s": 1671.8,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 14786.1,
+   "pp_tok_s": 1876.3,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3850.8,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 245.0,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 90.3,
+   "reps": [
+    91.0,
+    97.0,
+    82.8
+   ],
+   "hit_rate": 0.993905472636816,
+   "text": "The wind didn\u2019t just blow; it screamed. It tore through the iron gallery of the Blackwood Point Lighthouse, rattling the glass panes like a prisoner shaking its bars.\n\nElias Thorne was seventy years old, and he had been the keeper for forty of them. He knew every creak of the spiral staircase, every draft that slipped under the door, and every shift in the barometric pressure that preceded a storm. He was not merely a worker; he was the heartbeat of the coast.\n\nIt was November, the month of grey seas and shorter days. The fog had rolled in thick, a wall of white so dense that even the beam of the Fresnel lens seemed to struggle against it. Elias stood in the lantern room, his hands roughened by salt and rope, adjusting the rotation mechanism. The great lens, a cathedral of glass and brass, began its slow, rhythmic sweep. *Flash. Dark. Flash. Dark.*\n\nHe checked the log"
+  },
+  {
+   "name": "code",
+   "tok_s": 105.1,
+   "reps": [
+    98.4,
+    109.9,
+    107.0
+   ],
+   "hit_rate": 0.9949900793650793,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 492 windows; per window: wait for the GPU 15.016 ms, pool + plan 0.297 ms, host staging 0.517 ms, commit 0.404 ms",
+  "strata serve: stage 1: 492 windows; per window: wait for the GPU 5.775 ms, pool + plan 0.854 ms, host staging 0.001 ms, commit 0.210 ms",
+  "strata serve: stage 0: 561 windows; per window: wait for the GPU 15.257 ms, pool + plan 0.306 ms, host staging 0.455 ms, commit 0.408 ms",
+  "strata serve: stage 1: 561 windows; per window: wait for the GPU 5.852 ms, pool + plan 0.820 ms, host staging 0.001 ms, commit 0.210 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split auto)",
+  "strata generate: layer split: CUDA1 PCIe probe 57.7 GB/s -> pcie_frac 0.55",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 9.98 GiB free",
+  "strata generate: layer split auto: CUDA0 82 SMs at 1.86 GHz -> 0.48 ms per layer, 16.45 GiB for experts",
+  "strata generate: layer split auto: CUDA1 84 SMs at 2.81 GHz -> 0.31 ms per layer, 5.99 GiB for experts",
+  "strata generate: layer split auto: K=30 - predicted 20.8 ms per decode window; the caches hold 10684 of 12288 profiled pairs (~99.5% of the routed mass)",
+  "strata generate: expert cache auto: 18.62 GiB free, 700 MiB reserved -> 6634 slots",
+  "strata generate: expert cache 7680 slots, 14.23 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 30-47, expert cache 3004 slots (5.98 GiB), 3004 of its 4608 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-29",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-29 (CUDA0), 30-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 93.2% (5367 hits / 5760 lookups)",
+  "strata serve: decode expert cache hit rate: 93.7% (4049 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 96.7% (4178 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 97.7% (26272 hits / 26880 lookups)",
+  "strata serve: decode expert cache hit rate: 97.1% (4194 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 97.8% (110748 hits / 113280 lookups)",
+  "strata serve: decode expert cache hit rate: 99.6% (113787 hits / 114240 lookups)",
+  "strata serve: decode expert cache hit rate: 99.4% (127856 hits / 128640 lookups)",
+  "strata serve: decode expert cache hit rate: 96.3% (116528 hits / 120960 lookups)",
+  "strata serve: decode expert cache hit rate: 99.4% (116423 hits / 117120 lookups)",
+  "strata serve: decode expert cache hit rate: 99.5% (120354 hits / 120960 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-v-x3-auto.json

@@ -0,0 +1,89 @@
+{
+ "label": "v-x3-auto",
+ "extra": [
+  "--layer-split",
+  "auto"
+ ],
+ "gpus": "0,1,2",
+ "needles": [
+  {
+   "tokens": 16066,
+   "prompt_ms": 9525.4,
+   "pp_tok_s": 1686.6,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 15017.1,
+   "pp_tok_s": 1847.4,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 4039.6,
+  "turn2_tokens": 6660,
+  "reused": 6631,
+  "turn2_ms": 360.2,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 67.6,
+   "reps": [
+    59.8,
+    83.1,
+    59.9
+   ],
+   "hit_rate": 0.9967581085879247,
+   "text": "The wind didn\u2019t just blow; it screamed. It tore through the iron gallery of the Blackwood Point Lighthouse, rattling the glass panes like a prisoner shaking its bars.\n\nElias Thorne was seventy years old, and he had been the keeper for forty of them. He knew every creak in the spiral staircase, every draft that slipped under the door, and every shift in the weather that the barometer couldn\u2019t quite predict. He knew that when the fog rolled in thick enough to swallow the horizon, the world ceased to exist. There was only the light, the stone, and him.\n\nIt was November, the month of storms. The sea was a churning cauldron of grey and white, throwing itself against the granite base with the force of a battering ram. Elias stood in the lantern room, his hands rough as sandpaper, adjusting the massive Fresnel lens. The rotation mechanism groaned, a sound like a ship\u2019s anchor chain being h"
+  },
+  {
+   "name": "code",
+   "tok_s": 89.6,
+   "reps": [
+    81.0,
+    104.8,
+    83.0
+   ],
+   "hit_rate": 0.9975041387598007,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 2: 522 windows; per window: wait for the GPU 12.405 ms, pool + plan 0.242 ms, host staging 0.006 ms, commit 0.375 ms",
+  "strata serve: stage 0: 590 windows; per window: wait for the GPU 7.387 ms, pool + plan 0.549 ms, host staging 0.517 ms, commit 0.248 ms",
+  "strata serve: stage 1: 590 windows; per window: wait for the GPU 3.071 ms, pool + plan 0.011 ms, host staging 0.000 ms, commit 0.606 ms",
+  "strata serve: stage 2: 590 windows; per window: wait for the GPU 12.592 ms, pool + plan 0.250 ms, host staging 0.006 ms, commit 0.377 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 3 GPUs: CUDA0, then CUDA1,2 (split auto)",
+  "strata generate: layer split: CUDA1 PCIe probe 3.2 GB/s -> pcie_frac 0.00",
+  "strata generate: layer split: CUDA1 holds its weights, session; 16.67 GiB free",
+  "strata generate: layer split: CUDA2 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA2 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: layer split auto: CUDA0 84 SMs at 2.81 GHz -> 0.31 ms per layer, 8.30 GiB for experts",
+  "strata generate: layer split auto: CUDA1 68 SMs at 1.54 GHz -> 0.69 ms per layer, 13.50 GiB for experts",
+  "strata generate: layer split auto: CUDA2 82 SMs at 1.86 GHz -> 0.48 ms per layer, 14.14 GiB for experts",
+  "strata generate: layer split auto: K=22,23 - predicted 19.9 ms per decode window; the caches hold 11298 of 12288 profiled pairs (~99.7% of the routed mass)",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4640 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 22-22, expert cache 256 slots (0.52 GiB), 256 of its 256 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA2 runs layers 23-47, expert cache 6400 slots (12.82 GiB), 6400 of its 6400 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-21",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-21 (CUDA0), 22-22 (CUDA1), 23-47 (CUDA2), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 97.7% (5609 hits / 5739 lookups)",
+  "strata serve: decode expert cache hit rate: 98.7% (4256 hits / 4310 lookups)",
+  "strata serve: decode expert cache hit rate: 99.1% (4278 hits / 4315 lookups)",
+  "strata serve: decode expert cache hit rate: 99.0% (29862 hits / 30170 lookups)",
+  "strata serve: decode expert cache hit rate: 98.9% (4264 hits / 4313 lookups)",
+  "strata serve: decode expert cache hit rate: 98.6% (134418 hits / 136339 lookups)",
+  "strata serve: decode expert cache hit rate: 99.5% (116986 hits / 117525 lookups)",
+  "strata serve: decode expert cache hit rate: 99.7% (129134 hits / 129554 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-x2-auto-c1024.json

@@ -0,0 +1,84 @@
+{
+ "label": "x2-auto-c1024",
+ "extra": [
+  "--layer-split",
+  "auto",
+  "--prefill",
+  "1024"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 2726,
+   "prompt_ms": 2648.7,
+   "pp_tok_s": 1029.2,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 8379,
+   "prompt_ms": 5547.0,
+   "pp_tok_s": 1510.5,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 16066,
+   "prompt_ms": 10123.3,
+   "pp_tok_s": 1587.0,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 17652.0,
+   "pp_tok_s": 1571.7,
+   "found": true,
+   "answer": "willow-474<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 4379.9,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 235.5,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 82.7,
+   "hit_rate": 1.0,
+   "text": "The wind didn\u2019t just blow; it screamed. It tore through the iron gallery of the Blackwood Point Lighthouse, rattling the glass panes like a prisoner shaking its bars.\n\nElias Thorne was seventy years old, and he had been the keeper for forty of them. He knew every creak in the spiral staircase, every draft that slipped under the door, and every shift in the weather that the barometer couldn\u2019t quite predict. He knew that when the fog rolled in thick enough to swallow the horizon, the world ceased to exist. There was only the light, the stone, and him.\n\nIt was November, the month of storms. The sea was a churning cauldron of grey and white, throwing itself against the granite base with a violence that made the floorboards tremble. Elias stood by the lantern room, his hands wrapped around a mug of coffee that had gone cold hours ago. He wasn\u2019t drinking it. He was holding it for warmth."
+  },
+  {
+   "name": "code",
+   "tok_s": 111.1,
+   "hit_rate": 1.0,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv(file_path: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys being the header values\n    and values being the corresponding cell values.\n    \n    Args:\n        file_path: Path to the CSV file.\n        \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result = []\n    with open(file_path, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_basic():\n    \"\"\"Test basic CSV parsing with simple data.\"\"\"\n    import tempfile\n    import os\n    \n    # Create a temporary CSV"
+  }
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split auto)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: layer split auto: K=19 - the caches hold 12288 of 12288 profiled pairs (fullest device 99%)",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3613 slots",
+  "strata generate: expert cache 4864 slots, 8.76 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 19-47, expert cache 7424 slots (14.66 GiB), 7424 of its 7424 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-18",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-18 (CUDA0), 19-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 100.0% (5760 hits / 5760 lookups)",
+  "strata serve: decode expert cache hit rate: 100.0% (4320 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 100.0% (4320 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 100.0% (4320 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 100.0% (4320 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 100.0% (26400 hits / 26400 lookups)",
+  "strata serve: decode expert cache hit rate: 100.0% (4320 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 100.0% (130080 hits / 130080 lookups)",
+  "strata serve: decode expert cache hit rate: 100.0% (110400 hits / 110400 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-x2-auto.json

@@ -0,0 +1,82 @@
+{
+ "label": "x2-auto",
+ "extra": [
+  "--layer-split",
+  "auto"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 2726,
+   "prompt_ms": 2711.7,
+   "pp_tok_s": 1005.3,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 8379,
+   "prompt_ms": 5010.3,
+   "pp_tok_s": 1672.4,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 16066,
+   "prompt_ms": 8994.8,
+   "pp_tok_s": 1786.1,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 15497.2,
+   "pp_tok_s": 1790.2,
+   "found": true,
+   "answer": "willow-474<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 4050.3,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 249.7,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 83.0,
+   "hit_rate": 0.9920220447608565,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias had lived in the tower for thirty years, and he knew the difference between a gale and a hurricane by the way the glass rattled in its frame. Tonight, it was the latter. The sea was a churning cauldron of black ink and white foam, throwing itself against the granite base with the force of a battering ram.\n\nInside the lantern room, the air was thick with the smell of kerosene and old brass. Elias wiped his hands on his woolen trousers, leaving faint, oily smears on the fabric. He checked the clock. 11:42 PM. The rotation was due.\n\nHe reached for the crank handle, a heavy iron wheel worn smooth by decades of his own palms. With a grunt that matched the strain of his shoulders, he began to turn it. The massive Fresnel lens, a cathedral of glass and crystal, began its slow, hypnotic sweep"
+  },
+  {
+   "name": "code",
+   "tok_s": 101.8,
+   "hit_rate": 0.991767530342175,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split auto)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: layer split auto: K=19 - the caches hold 11767 of 12288 profiled pairs (fullest device 100%)",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4606 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 19-47, expert cache 7160 slots (14.14 GiB), 7160 of its 7424 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-18",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-18 (CUDA0), 19-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 98.5% (6141 hits / 6234 lookups)",
+  "strata serve: decode expert cache hit rate: 98.9% (3797 hits / 3838 lookups)",
+  "strata serve: decode expert cache hit rate: 99.1% (3804 hits / 3838 lookups)",
+  "strata serve: decode expert cache hit rate: 99.4% (3816 hits / 3839 lookups)",
+  "strata serve: decode expert cache hit rate: 99.6% (3825 hits / 3839 lookups)",
+  "strata serve: decode expert cache hit rate: 99.5% (27693 hits / 27832 lookups)",
+  "strata serve: decode expert cache hit rate: 99.4% (3815 hits / 3839 lookups)",
+  "strata serve: decode expert cache hit rate: 99.2% (127081 hits / 128103 lookups)",
+  "strata serve: decode expert cache hit rate: 99.2% (119386 hits / 120377 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-x2-k16.json

@@ -0,0 +1,81 @@
+{
+ "label": "x2-k16",
+ "extra": [
+  "--layer-split",
+  "16"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 2726,
+   "prompt_ms": 2987.1,
+   "pp_tok_s": 912.6,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 8379,
+   "prompt_ms": 5908.6,
+   "pp_tok_s": 1418.1,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 16066,
+   "prompt_ms": 10655.8,
+   "pp_tok_s": 1507.7,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 18484.6,
+   "pp_tok_s": 1500.9,
+   "found": true,
+   "answer": "willow-474<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 4790.8,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 243.3,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 71.4,
+   "hit_rate": 0.9814261642156863,
+   "text": "The wind didn\u2019t just blow; it screamed. It clawed at the granite base of the tower, trying to pry the lighthouse from its bedrock. Inside, however, the air was still, smelling faintly of kerosene and old paper.\n\nElias had been the keeper of the Point for thirty-two years. He knew every creak in the floorboards, every draft that slipped through the window seals, and exactly how much oil the great Fresnel lens needed to turn its slow, hypnotic rotation.\n\nIt was 2:00 AM. The storm was at its peak. The sea was a chaotic black mirror, whipped into whitecaps that looked like jagged teeth.\n\nElias climbed the spiral stairs, his hand gripping the cold iron railing. His boots, heavy with salt and wear, thumped a steady rhythm against the stone. *Thump. Thump. Thump.*\n\nAt the top, the lantern room hummed with the vibration of"
+  },
+  {
+   "name": "code",
+   "tok_s": 86.4,
+   "hit_rate": 0.9798276439089693,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 16)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4096 slots, 7.17 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 16-47, expert cache 7124 slots (14.14 GiB), 7124 of its 8192 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-15",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-15 (CUDA0), 16-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 97.7% (5626 hits / 5760 lookups)",
+  "strata serve: decode expert cache hit rate: 98.1% (4237 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 98.8% (4269 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 99.1% (4279 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 99.5% (4298 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 98.9% (28471 hits / 28800 lookups)",
+  "strata serve: decode expert cache hit rate: 99.1% (4282 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 98.1% (128135 hits / 130560 lookups)",
+  "strata serve: decode expert cache hit rate: 98.0% (117109 hits / 119520 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-x2-k22.json

@@ -0,0 +1,81 @@
+{
+ "label": "x2-k22",
+ "extra": [
+  "--layer-split",
+  "22"
+ ],
+ "gpus": "0,2",
+ "needles": [
+  {
+   "tokens": 2726,
+   "prompt_ms": 2537.7,
+   "pp_tok_s": 1074.2,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 8379,
+   "prompt_ms": 4440.0,
+   "pp_tok_s": 1887.2,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 16066,
+   "prompt_ms": 7872.5,
+   "pp_tok_s": 2040.8,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 13405.0,
+   "pp_tok_s": 2069.6,
+   "found": true,
+   "answer": "willow-474<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 3610.4,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 236.0,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 78.1,
+   "hit_rate": 0.9851122208995093,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was seventy-three years old, and he had been the keeper of the Blackwood Point Light for forty of those years. The other thirty-three had been spent in a hospital bed, waiting for the end.\n\nEvery night, Elias climbed the one hundred and twelve steps of the spiral staircase. His knees, worn smooth by the friction of his own boots over decades, protested with a sharp ache. He counted them. *One, two, three\u2026* The rhythm was his heartbeat. If he lost the count, he lost the light.\n\nAt the top, the lantern room hummed with the low, electric thrum of the Fresnel lens. It was a cathedral of glass and brass, a machine that had never failed him. Not once. Not in four decades.\n\nHe polished the brass railing with a rag that smelled of lemon and"
+  },
+  {
+   "name": "code",
+   "tok_s": 104.3,
+   "hit_rate": 0.9842543225870746,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split 22)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 18.13 GiB free",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4640 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 22-47, expert cache 6656 slots (13.34 GiB), 6656 of its 6656 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-21",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-21 (CUDA0), 22-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 97.7% (5609 hits / 5739 lookups)",
+  "strata serve: decode expert cache hit rate: 98.5% (4241 hits / 4306 lookups)",
+  "strata serve: decode expert cache hit rate: 98.9% (4262 hits / 4309 lookups)",
+  "strata serve: decode expert cache hit rate: 99.4% (4290 hits / 4315 lookups)",
+  "strata serve: decode expert cache hit rate: 99.6% (4303 hits / 4319 lookups)",
+  "strata serve: decode expert cache hit rate: 98.8% (28379 hits / 28721 lookups)",
+  "strata serve: decode expert cache hit rate: 99.3% (4285 hits / 4314 lookups)",
+  "strata serve: decode expert cache hit rate: 98.5% (135713 hits / 137764 lookups)",
+  "strata serve: decode expert cache hit rate: 98.4% (118518 hits / 120414 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-x2r-auto.json

@@ -0,0 +1,82 @@
+{
+ "label": "x2r-auto",
+ "extra": [
+  "--layer-split",
+  "auto"
+ ],
+ "gpus": "2,0",
+ "needles": [
+  {
+   "tokens": 2726,
+   "prompt_ms": 2804.2,
+   "pp_tok_s": 972.1,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 8379,
+   "prompt_ms": 5641.7,
+   "pp_tok_s": 1485.2,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 16066,
+   "prompt_ms": 10643.4,
+   "pp_tok_s": 1509.5,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 18363.5,
+   "pp_tok_s": 1510.8,
+   "found": true,
+   "answer": "willow-474<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 4517.2,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 245.6,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 78.9,
+   "hit_rate": 0.9913117283950618,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his woolen collar up to his chin, the fabric stiff with salt and ice. Outside the thick glass of the lantern room, the Atlantic was a churning cauldron of black and white, the waves crashing against the granite base with a violence that shook the very foundations of the tower. It was November, 1924, and the storm had been raging for three days.\n\nElias was not a man who feared the dark. He was a man who feared the silence.\n\nHe checked the clock on the wall. 11:42 PM. The rotation of the great Fresnel lens was steady, a rhythmic *whirrr-click, whirrr-click* that seemed to sync with his own heartbeat. He had been doing this for forty years. His hands were mapped with scars from rope burns and broken glass, his eyes permanently squinted against the glare of the bulb."
+  },
+  {
+   "name": "code",
+   "tok_s": 93.4,
+   "hit_rate": 0.990286044973545,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split auto)",
+  "strata generate: layer split: CUDA1 PCIe probe 57.7 GB/s -> pcie_frac 0.55",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 9.98 GiB free",
+  "strata generate: layer split auto: K=36 - the caches hold 11775 of 12288 profiled pairs (fullest device 100%)",
+  "strata generate: expert cache auto: 18.62 GiB free, 700 MiB reserved -> 6634 slots",
+  "strata generate: expert cache 8828 slots, 16.45 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 36-47, expert cache 2945 slots (5.99 GiB), 2945 of its 3072 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-35",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-35 (CUDA0), 36-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 98.6% (5678 hits / 5760 lookups)",
+  "strata serve: decode expert cache hit rate: 99.1% (4283 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 99.2% (4285 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 99.6% (4303 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 99.7% (4306 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 99.5% (27700 hits / 27840 lookups)",
+  "strata serve: decode expert cache hit rate: 99.4% (4295 hits / 4320 lookups)",
+  "strata serve: decode expert cache hit rate: 99.1% (128474 hits / 129600 lookups)",
+  "strata serve: decode expert cache hit rate: 99.0% (119785 hits / 120960 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-x2t-auto.json

@@ -0,0 +1,99 @@
+{
+ "label": "x2t-auto",
+ "extra": [
+  "--layer-split",
+  "auto"
+ ],
+ "gpus": "0,1",
+ "needles": [
+  {
+   "tokens": 2726,
+   "prompt_ms": 4201.1,
+   "pp_tok_s": 648.9,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 8379,
+   "prompt_ms": 9655.6,
+   "pp_tok_s": 867.8,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 16066,
+   "prompt_ms": 17573.8,
+   "pp_tok_s": 914.2,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 30615.6,
+   "pp_tok_s": 906.2,
+   "found": true,
+   "answer": "willow-474<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 7864.7,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 366.9,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 45.5,
+   "reps": [
+    45.5
+   ],
+   "hit_rate": 0.9703345151405784,
+   "text": "The wind didn\u2019t just blow; it screamed.\n\nElias pulled his wool coat tighter around his shoulders, the fabric stiff with salt and age. He was seventy years old, but he moved with the grace of a man who had spent decades on a narrow spiral staircase. His hands, rough as sandpaper, knew every bolt, every lever, and every creak in the iron bones of the tower.\n\nFor forty years, Elias had been the guardian of the Point. Not just of the light, but of the silence between the waves.\n\nIt was November. The sky was a bruised purple, heavy with rain that hadn\u2019t yet fallen. The sea was a churning cauldron of grey and white, throwing itself against the granite base with a violence that shook the floorboards beneath Elias\u2019s boots.\n\nHe climbed the stairs. One hundred and twelve steps. He counted them by feel, his left hand trailing along the cold iron railing. At the top, the air was"
+  },
+  {
+   "name": "code",
+   "tok_s": 58.0,
+   "reps": [
+    58.0
+   ],
+   "hit_rate": 0.9700542735219787,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv_to_dicts(filepath: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys from the header and values from the row.\n    \n    Args:\n        filepath: Path to the CSV file.\n    \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result: List[Dict[str, Any]] = []\n    with open(filepath, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_to_dicts():\n    import tempfile\n    import os\n    \n    # Create a temporary CSV file\n    with tempfile.NamedTemporaryFile"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 0: 168 windows; per window: wait for the GPU 9.683 ms, pool + plan 0.509 ms, host staging 0.714 ms, commit 0.320 ms",
+  "strata serve: stage 1: 168 windows; per window: wait for the GPU 25.253 ms, pool + plan 0.881 ms, host staging 0.000 ms, commit 0.559 ms",
+  "strata serve: stage 0: 242 windows; per window: wait for the GPU 9.860 ms, pool + plan 0.550 ms, host staging 0.750 ms, commit 0.328 ms",
+  "strata serve: stage 1: 242 windows; per window: wait for the GPU 26.029 ms, pool + plan 0.980 ms, host staging 0.000 ms, commit 0.571 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split auto)",
+  "strata generate: layer split: CUDA1 PCIe probe 3.2 GB/s -> pcie_frac 0.00",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 16.18 GiB free",
+  "strata generate: layer split auto: K=20 - the caches hold 10761 of 12288 profiled pairs (fullest device 100%)",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4603 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 20-47, expert cache 6157 slots (12.19 GiB), 6157 of its 7168 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-19",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-19 (CUDA0), 20-47 (CUDA1), one hand-off per window",
+  "strata generate: layer split across 2 GPUs: CUDA0, then CUDA1 (split auto)",
+  "strata generate: layer split: CUDA1 PCIe probe 3.2 GB/s -> pcie_frac 0.00",
+  "strata generate: layer split: CUDA1 holds its weights, session and head; 16.18 GiB free",
+  "strata generate: layer split auto: K=20 - the caches hold 10761 of 12288 profiled pairs (fullest device 100%)",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3345 slots",
+  "strata generate: expert cache 4603 slots, 8.29 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 20-47, expert cache 6157 slots (12.19 GiB), 6157 of its 7168 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-19",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-19 (CUDA0), 20-47 (CUDA1), one hand-off per window",
+  "strata serve: decode expert cache hit rate: 96.6% (5559 hits / 5754 lookups)",
+  "strata serve: decode expert cache hit rate: 97.5% (4205 hits / 4315 lookups)",
+  "strata serve: decode expert cache hit rate: 97.8% (4217 hits / 4312 lookups)",
+  "strata serve: decode expert cache hit rate: 98.6% (4257 hits / 4318 lookups)"
+ ]
+}

bench/results/2026-09-29-layer-split/data/pp-x3-auto.json

@@ -0,0 +1,99 @@
+{
+ "label": "x3-auto",
+ "extra": [
+  "--layer-split",
+  "auto"
+ ],
+ "gpus": "0,2,1",
+ "needles": [
+  {
+   "tokens": 2726,
+   "prompt_ms": 3657.4,
+   "pp_tok_s": 745.3,
+   "found": true,
+   "answer": "meadow-254<|im_end|>"
+  },
+  {
+   "tokens": 8379,
+   "prompt_ms": 7594.1,
+   "pp_tok_s": 1103.4,
+   "found": true,
+   "answer": "juniper-766<|im_end|>"
+  },
+  {
+   "tokens": 16066,
+   "prompt_ms": 13996.4,
+   "pp_tok_s": 1147.9,
+   "found": true,
+   "answer": "falcon-174<|im_end|>"
+  },
+  {
+   "tokens": 27743,
+   "prompt_ms": 24255.2,
+   "pp_tok_s": 1143.8,
+   "found": true,
+   "answer": "willow-474<|im_end|>"
+  }
+ ],
+ "chat": {
+  "turn1_tokens": 6584,
+  "turn1_ms": 6104.9,
+  "turn2_tokens": 6660,
+  "reused": 6632,
+  "turn2_ms": 393.4,
+  "answer": "lantern-417<|im_end|>",
+  "ok": true
+ },
+ "decode": [
+  {
+   "name": "story",
+   "tok_s": 51.9,
+   "reps": [
+    51.9
+   ],
+   "hit_rate": 1.0,
+   "text": "The wind didn\u2019t just blow; it screamed. It tore through the iron gallery of the Blackwood Point Lighthouse, rattling the glass panes like a prisoner shaking its bars.\n\nElias Thorne was seventy years old, and he had been the keeper for forty of them. He knew every creak in the spiral staircase, every draft that slipped under the door, and every shift in the weather that the barometer couldn\u2019t quite predict. He knew that when the fog rolled in thick enough to swallow the horizon, the world ceased to exist. There was only the light, the stone, and him.\n\nIt was November, the month of storms. The sea was a churning cauldron of grey and white, throwing itself against the granite base with a violence that made the floorboards tremble. Elias stood by the lantern room, his hands wrapped around a mug of coffee that had gone cold hours ago. He wasn\u2019t drinking it. He was holding it for warmth."
+  },
+  {
+   "name": "code",
+   "tok_s": 69.7,
+   "reps": [
+    69.7
+   ],
+   "hit_rate": 1.0,
+   "text": "```python\nimport csv\nfrom typing import List, Dict, Any\n\n\ndef parse_csv(file_path: str) -> List[Dict[str, Any]]:\n    \"\"\"\n    Parse a CSV file into a list of dictionaries.\n    \n    Each dictionary represents a row, with keys being the header values\n    and values being the corresponding cell values.\n    \n    Args:\n        file_path: Path to the CSV file.\n        \n    Returns:\n        A list of dictionaries, one per row (excluding the header).\n    \"\"\"\n    result = []\n    with open(file_path, 'r', newline='', encoding='utf-8') as f:\n        reader = csv.DictReader(f)\n        for row in reader:\n            result.append(dict(row))\n    return result\n\n\n# Tests\ndef test_parse_csv_basic():\n    \"\"\"Test basic CSV parsing with simple data.\"\"\"\n    import tempfile\n    import os\n    \n    # Create a temporary CSV"
+  }
+ ],
+ "stage_timing": [
+  "strata serve: stage 2: 165 windows; per window: wait for the GPU 13.452 ms, pool + plan 0.162 ms, host staging 0.000 ms, commit 0.328 ms",
+  "strata serve: stage 0: 234 windows; per window: wait for the GPU 6.235 ms, pool + plan 0.145 ms, host staging 0.704 ms, commit 0.214 ms",
+  "strata serve: stage 1: 234 windows; per window: wait for the GPU 15.592 ms, pool + plan 0.246 ms, host staging 0.000 ms, commit 0.657 ms",
+  "strata serve: stage 2: 234 windows; per window: wait for the GPU 13.916 ms, pool + plan 0.177 ms, host staging 0.000 ms, commit 0.335 ms"
+ ],
+ "engine_lines": [
+  "strata generate: layer split across 3 GPUs: CUDA0, then CUDA1,2 (split auto)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session; 18.62 GiB free",
+  "strata generate: layer split: CUDA2 PCIe probe 3.2 GB/s -> pcie_frac 0.00",
+  "strata generate: layer split: CUDA2 holds its weights, session and head; 16.18 GiB free",
+  "strata generate: layer split auto: K=12,33 - the caches hold 12288 of 12288 profiled pairs (fullest device 66%)",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3072 slots",
+  "strata generate: expert cache 3072 slots, 5.41 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 12-32, expert cache 5376 slots (10.22 GiB), 5376 of its 5376 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA2 runs layers 33-47, expert cache 3840 slots (7.79 GiB), 3840 of its 3840 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-11",
+  "strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)",
+  "strata serve: layer split: layers 0-11 (CUDA0), 12-32 (CUDA1), 33-47 (CUDA2), one hand-off per window",
+  "strata generate: layer split across 3 GPUs: CUDA0, then CUDA1,2 (split auto)",
+  "strata generate: layer split: CUDA1 PCIe probe 6.4 GB/s -> pcie_frac 0.14",
+  "strata generate: layer split: CUDA1 holds its weights, session; 18.62 GiB free",
+  "strata generate: layer split: CUDA2 PCIe probe 3.2 GB/s -> pcie_frac 0.00",
+  "strata generate: layer split: CUDA2 holds its weights, session and head; 16.18 GiB free",
+  "strata generate: layer split auto: K=12,33 - the caches hold 12288 of 12288 profiled pairs (fullest device 66%)",
+  "strata generate: expert cache auto: 10.46 GiB free, 700 MiB reserved -> 3072 slots",
+  "strata generate: expert cache 3072 slots, 5.41 GiB of VRAM; policy is",
+  "strata generate: layer split: CUDA1 runs layers 12-32, expert cache 5376 slots (10.22 GiB), 5376 of its 5376 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA2 runs layers 33-47, expert cache 3840 slots (7.79 GiB), 3840 of its 3840 profiled pairs; slot 0 verified",
+  "strata generate: layer split: CUDA0 runs layers 0-11"
+ ]
+}

bench/results/2026-09-29-rtx3090-epyc-milan/README.md

@@ -0,0 +1,46 @@
+# Preliminary native RTX 3090 / EPYC 7453 results
+
+Issue: [#165](https://github.com/Niko1221/Strata/issues/165)
+Engine: Strata v0.1.26, source build at `ac8b251`
+Status: preliminary; prompt set and harness guidance requested upstream.
+
+## Hardware
+
+| Component | Guest-visible details |
+|---|---|
+| CPU | AMD EPYC 7453, 20 vCPU, AVX2; AVX-512 not exposed |
+| RAM | 165 GiB visible to Ubuntu 24.04.5 KVM guest; physical DIMM layout and bandwidth not verified |
+| GPUs | 2x RTX 3090 24 GB; PCIe Gen4 x16 maximum reported per card; driver 595.91.07 |
+| Power limit | 280 W configured on each GPU; defaults are 350 W / 420 W, max-adjustable limits 366 W / 450 W |
+| Storage | 541 GiB ext4 guest data disk; host storage layout not verified |
+
+The power values above are configured caps, not measured workload draw. Idle draw during the hardware capture was approximately 35 W / 29 W.
+
+## Method
+
+Native Linux setup, local build from v0.1.26, `--prefill auto`, shipped expert profile, automatic expert cache, int8 KV, MTP on, images off, experimental speed projection off. The GPU power limit was 280 W per card. Native runs used a systemd service with `LimitMEMLOCK=infinity`; other llama-swap model containers were stopped.
+
+The local API harness used the public Strata source tree as its prompt corpus, with generated tasks, `temperature: 0`, `reasoning_effort: none`, and `max_tokens: 256`. It is not the upstream code-agent prompt set or harness. Runs use unique request IDs and no conversation reuse in speed mode. Three runs per speed cell are summarized by medians; actual `usage.prompt_tokens` are recorded because nominal context labels can drift. The first decode run is also shown. Several requests ended early on EOS, so actual generated counts are in the raw JSON.
+
+No calibration comparison, upstream prompt comparison, `STRATA_SPLIT_TIMING` stage timing, or under-load power-draw capture has been done. Treat all prompt/decode comparisons with upstream as indicative only until the requested upstream method is available.
+
+## Results
+
+See [`matrix.md`](matrix.md) for summary tables and [`matrix.json`](matrix.json) for all successful run records. Per-run source JSON, logs, the local harness, and scrubbed hardware facts are in [`data/`](data/).
+
+Highlights:
+
+- IQ3_XXS on one 3090: 1K–262K cells, three runs each; 262K prompts were 232,183 / 259,589 / 261,068 tokens and fit within the 262,144 context.
+- Coder IQ1_M at 32K: single-GPU median decode 66.8 tok/s; dual-GPU auto (K=19) median 98.6 tok/s.
+- Fixed Coder K sweep: K=22 was the highest observed three-run median (103.3 tok/s); independently generated prompts mean this is not a paired ranking.
+- IQ3_XXS and IQ3_S dual-GPU auto both selected K=24 at 32K.
+- IQ3_XXS and IQ3_S needles passed 3/3 at 8K / 16K / 28K on the tested single/dual configurations; two-turn checkpoint reuse passed for both.
+
+## Limits and follow-up
+
+- Upstream prompts/harness are not yet available; all current speed data uses a local source-tree corpus.
+- The guest exposes one NUMA node and 165 GiB RAM, but physical DIMM topology and memory bandwidth are unknown.
+- PCIe x16 is the reported maximum link width; the engine probes were about 23–26 GB/s. Verify PCIe generation/width under sustained load before claiming a direct x16-vs-x4 comparison.
+- Coder dual-GPU needle/two-turn checks and dual-GPU timing breakdowns are not run yet.
+- K=18 has one successful run at 83.1 tok/s; a repeated startup failed while uploading a dense weight with an out-of-memory error, so it is not a three-run median.
+- Calibration/default comparisons and IQ3_S single-GPU results remain outstanding.

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-1x3090/speed-32k-1.json

@@ -0,0 +1,360 @@
+{
+ "label": "native-v0.1.26-Coder-1x3090",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 1,
+ "run_id": "6c1252339f83",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:11:07",
+ "prompt_tokens": 28317,
+ "completion_tokens": 48,
+ "ttft_s": 12.868,
+ "e2e_s": 13.739,
+ "api_prompt_tps": 2200.5,
+ "api_decode_tps": 54.0,
+ "engine_prompt_tps": 2229.2,
+ "engine_decode_tps": 52.7,
+ "log_lines": [
+  "strata serve: prompt 28317 tokens = 0 reused + 28317 read in 12703 ms (2229.2 tok/s), 48 generated in 911 ms (52.7 tok/s), drafts accepted 31 of 38, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 96.3% (25001 hits / 25956 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what's there and identify the last file.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 8973,
+   "expert_cache_mib": 17503,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 369,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790716268.10927,
+    "duration_s": 13.6,
+    "finish": "stop",
+    "prompt_tokens": 28317,
+    "reused": 0,
+    "output_tokens": 48,
+    "engine_generated": 48,
+    "prompt_ms": 12702.6,
+    "decode_ms": 910.6,
+    "decode_tok_s": 52.7,
+    "hit_rate": 0.963
+   }
+  ],
+  "requests_kept": 1,
+  "totals": {
+   "since": 1790716256.7391467,
+   "requests": 1,
+   "prompt_tokens": 28317,
+   "reused": 0,
+   "output_tokens": 48,
+   "prompt_ms": 12702.6,
+   "decode_ms": 910.6
+  },
+  "hardware": {
+   "gpu_util": 88,
+   "gpu_mem_used": 25531711488,
+   "gpu_mem_total": 25769803776,
+   "gpu_temp": 46,
+   "gpu_power": 220.362,
+   "gpu_power_limit": 280.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 0.28515625,
+   "gpu_pcie_tx_mb": 0.4287109375,
+   "cpu": 81.3,
+   "ram_used": 43964985344,
+   "ram_total": 177175990272,
+   "disk_read_mb": 2.9148478336133063,
+   "disk_write_mb": 0.0,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090",
+   "gpu_count": 1,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    1,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    99,
+    100,
+    100,
+    96,
+    100,
+    99,
+    100,
+    99,
+    99,
+    100,
+    100,
+    88
+   ],
+   "gpu_mem_used": [
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25407979520,
+    25418465280,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25531711488
+   ],
+   "gpu_temp": [
+    43,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    46,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    46
+   ],
+   "gpu_power": [
+    148.8,
+    140.48,
+    132.59,
+    119.03,
+    118.99,
+    119.03,
+    119.04,
+    119.03,
+    119.12,
+    119.17,
+    119.16,
+    119.15,
+    119.26,
+    191.57,
+    276.49,
+    276.88,
+    275.95,
+    277.04,
+    277.35,
+    267.91,
+    275.37,
+    276.16,
+    278.28,
+    279.07,
+    220.36
+   ],
+   "gpu_pcie_rx_mb": [
+    0.33,
+    0.33,
+    0.29,
+    0.29,
+    0.33,
+    0.33,
+    0.33,
+    0.29,
+    0.33,
+    0.29,
+    0.33,
+    0.29,
+    385.14,
+    19.88,
+    1892.23,
+    13280.39,
+    85.45,
+    16838.55,
+    680.06,
+    1060.72,
+    13.45,
+    15.74,
+    5013.75,
+    1194.52,
+    0.29
+   ],
+   "cpu": [
+    0.0,
+    0.7,
+    7.3,
+    15.7,
+    7.1,
+    2.0,
+    1.2,
+    2.0,
+    2.1,
+    1.6,
+    1.9,
+    7.4,
+    13.9,
+    18.3,
+    6.1,
+    6.0,
+    16.7,
+    24.9,
+    13.2,
+    12.0,
+    7.1,
+    6.2,
+    6.0,
+    8.8,
+    81.3
+   ],
+   "ram_used": [
+    43381886976,
+    43381694464,
+    43410796544,
+    43434872832,
+    43483377664,
+    43485900800,
+    43484897280,
+    43481210880,
+    43469135872,
+    43462295552,
+    43458363392,
+    43496140800,
+    43624353792,
+    43648593920,
+    43633405952,
+    43641139200,
+    43635249152,
+    43689267200,
+    43846070272,
+    43924541440,
+    43924467712,
+    43918565376,
+    43883311104,
+    44002877440,
+    43964985344
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.01,
+    0.0,
+    0.0,
+    0.0,
+    25.43,
+    204.93,
+    214.14,
+    7.41,
+    0.22,
+    184.19,
+    135.03,
+    0.0,
+    101.27,
+    0.0,
+    0.0,
+    0.0,
+    0.78,
+    2.91
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790716282.234284
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-1x3090/speed-32k-2.json

@@ -0,0 +1,491 @@
+{
+ "label": "native-v0.1.26-Coder-1x3090",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 2,
+ "run_id": "894af0ad69b7",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:11:22",
+ "prompt_tokens": 31630,
+ "completion_tokens": 26,
+ "ttft_s": 12.792,
+ "e2e_s": 13.164,
+ "api_prompt_tps": 2472.7,
+ "api_decode_tps": 67.3,
+ "engine_prompt_tps": 2506.6,
+ "engine_decode_tps": 66.8,
+ "log_lines": [
+  "strata serve: prompt 31630 tokens = 0 reused + 31630 read in 12619 ms (2506.6 tok/s), 26 generated in 389 ms (66.8 tok/s), drafts accepted 12 of 21, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 99.1% (16646 hits / 16791 lookups)"
+ ],
+ "answer_head": "I don't see any file content in the conversation above. Could you please share the file you'd like me to analyze?",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 8973,
+   "expert_cache_mib": 17503,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 369,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790716282.3818104,
+    "duration_s": 13.0,
+    "finish": "stop",
+    "prompt_tokens": 31630,
+    "reused": 0,
+    "output_tokens": 26,
+    "engine_generated": 26,
+    "prompt_ms": 12618.8,
+    "decode_ms": 389.0,
+    "decode_tok_s": 66.8,
+    "hit_rate": 0.991
+   },
+   {
+    "projection": null,
+    "time": 1790716268.10927,
+    "duration_s": 13.6,
+    "finish": "stop",
+    "prompt_tokens": 28317,
+    "reused": 0,
+    "output_tokens": 48,
+    "engine_generated": 48,
+    "prompt_ms": 12702.6,
+    "decode_ms": 910.6,
+    "decode_tok_s": 52.7,
+    "hit_rate": 0.963
+   }
+  ],
+  "requests_kept": 2,
+  "totals": {
+   "since": 1790716256.7391467,
+   "requests": 2,
+   "prompt_tokens": 59947,
+   "reused": 0,
+   "output_tokens": 74,
+   "prompt_ms": 25321.4,
+   "decode_ms": 1299.6
+  },
+  "hardware": {
+   "gpu_util": 81,
+   "gpu_mem_used": 25531711488,
+   "gpu_mem_total": 25769803776,
+   "gpu_temp": 45,
+   "gpu_power": 256.109,
+   "gpu_power_limit": 280.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 9.7744140625,
+   "gpu_pcie_tx_mb": 25.1767578125,
+   "cpu": 46.1,
+   "ram_used": 43872071680,
+   "ram_total": 177175990272,
+   "disk_read_mb": 1.6222807345356267,
+   "disk_write_mb": 0.018689870213544086,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090",
+   "gpu_count": 1,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    1,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    99,
+    100,
+    100,
+    96,
+    100,
+    99,
+    100,
+    99,
+    99,
+    100,
+    100,
+    88,
+    0,
+    100,
+    99,
+    100,
+    99,
+    100,
+    98,
+    99,
+    99,
+    100,
+    99,
+    100,
+    81
+   ],
+   "gpu_mem_used": [
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25407979520,
+    25418465280,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488
+   ],
+   "gpu_temp": [
+    43,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    46,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    46,
+    44,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    48,
+    47,
+    45
+   ],
+   "gpu_power": [
+    148.8,
+    140.48,
+    132.59,
+    119.03,
+    118.99,
+    119.03,
+    119.04,
+    119.03,
+    119.12,
+    119.17,
+    119.16,
+    119.15,
+    119.26,
+    191.57,
+    276.49,
+    276.88,
+    275.95,
+    277.04,
+    277.35,
+    267.91,
+    275.37,
+    276.16,
+    278.28,
+    279.07,
+    220.36,
+    189.89,
+    258.72,
+    276.75,
+    276.67,
+    277.52,
+    275.34,
+    268.93,
+    277.69,
+    277.77,
+    276.91,
+    278.53,
+    278.56,
+    256.11
+   ],
+   "gpu_pcie_rx_mb": [
+    0.33,
+    0.33,
+    0.29,
+    0.29,
+    0.33,
+    0.33,
+    0.33,
+    0.29,
+    0.33,
+    0.29,
+    0.33,
+    0.29,
+    385.14,
+    19.88,
+    1892.23,
+    13280.39,
+    85.45,
+    16838.55,
+    680.06,
+    1060.72,
+    13.45,
+    15.74,
+    5013.75,
+    1194.52,
+    0.29,
+    2531.19,
+    14.02,
+    3715.09,
+    10.68,
+    13440.37,
+    8568.48,
+    14.92,
+    15.31,
+    15.69,
+    6486.56,
+    17.31,
+    9674.45,
+    9.77
+   ],
+   "cpu": [
+    0.0,
+    0.7,
+    7.3,
+    15.7,
+    7.1,
+    2.0,
+    1.2,
+    2.0,
+    2.1,
+    1.6,
+    1.9,
+    7.4,
+    13.9,
+    18.3,
+    6.1,
+    6.0,
+    16.7,
+    24.9,
+    13.2,
+    12.0,
+    7.1,
+    6.2,
+    6.0,
+    8.8,
+    81.3,
+    4.2,
+    6.8,
+    6.4,
+    7.6,
+    5.5,
+    6.0,
+    20.6,
+    12.9,
+    6.2,
+    7.0,
+    5.7,
+    5.9,
+    46.1
+   ],
+   "ram_used": [
+    43381886976,
+    43381694464,
+    43410796544,
+    43434872832,
+    43483377664,
+    43485900800,
+    43484897280,
+    43481210880,
+    43469135872,
+    43462295552,
+    43458363392,
+    43496140800,
+    43624353792,
+    43648593920,
+    43633405952,
+    43641139200,
+    43635249152,
+    43689267200,
+    43846070272,
+    43924541440,
+    43924467712,
+    43918565376,
+    43883311104,
+    44002877440,
+    43964985344,
+    43959267328,
+    43943862272,
+    43937861632,
+    43930320896,
+    43922284544,
+    43915001856,
+    43817238528,
+    43819147264,
+    43818729472,
+    43828027392,
+    43824201728,
+    43825434624,
+    43872071680
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.01,
+    0.0,
+    0.0,
+    0.0,
+    25.43,
+    204.93,
+    214.14,
+    7.41,
+    0.22,
+    184.19,
+    135.03,
+    0.0,
+    101.27,
+    0.0,
+    0.0,
+    0.0,
+    0.78,
+    2.91,
+    0.61,
+    0.0,
+    0.0,
+    0.02,
+    0.0,
+    0.0,
+    79.64,
+    41.92,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    1.62
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790716295.9009006
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-1x3090/speed-32k-3.json

@@ -0,0 +1,622 @@
+{
+ "label": "native-v0.1.26-Coder-1x3090",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 3,
+ "run_id": "a4c63bd599ab",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:11:35",
+ "prompt_tokens": 31601,
+ "completion_tokens": 45,
+ "ttft_s": 12.796,
+ "e2e_s": 13.243,
+ "api_prompt_tps": 2469.6,
+ "api_decode_tps": 98.5,
+ "engine_prompt_tps": 2502.4,
+ "engine_decode_tps": 97.4,
+ "log_lines": [
+  "strata serve: prompt 31601 tokens = 0 reused + 31601 read in 12628 ms (2502.4 tok/s), 45 generated in 462 ms (97.4 tok/s), drafts accepted 33 of 37, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 98.6% (23985 hits / 24333 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what we're working with.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 8973,
+   "expert_cache_mib": 17503,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 369,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790716296.0458817,
+    "duration_s": 13.1,
+    "finish": "stop",
+    "prompt_tokens": 31601,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 12628.3,
+    "decode_ms": 461.9,
+    "decode_tok_s": 97.4,
+    "hit_rate": 0.986
+   },
+   {
+    "projection": null,
+    "time": 1790716282.3818104,
+    "duration_s": 13.0,
+    "finish": "stop",
+    "prompt_tokens": 31630,
+    "reused": 0,
+    "output_tokens": 26,
+    "engine_generated": 26,
+    "prompt_ms": 12618.8,
+    "decode_ms": 389.0,
+    "decode_tok_s": 66.8,
+    "hit_rate": 0.991
+   },
+   {
+    "projection": null,
+    "time": 1790716268.10927,
+    "duration_s": 13.6,
+    "finish": "stop",
+    "prompt_tokens": 28317,
+    "reused": 0,
+    "output_tokens": 48,
+    "engine_generated": 48,
+    "prompt_ms": 12702.6,
+    "decode_ms": 910.6,
+    "decode_tok_s": 52.7,
+    "hit_rate": 0.963
+   }
+  ],
+  "requests_kept": 3,
+  "totals": {
+   "since": 1790716256.7391467,
+   "requests": 3,
+   "prompt_tokens": 91548,
+   "reused": 0,
+   "output_tokens": 119,
+   "prompt_ms": 37949.7,
+   "decode_ms": 1761.5
+  },
+  "hardware": {
+   "gpu_util": 96,
+   "gpu_mem_used": 25531711488,
+   "gpu_mem_total": 25769803776,
+   "gpu_temp": 47,
+   "gpu_power": 245.399,
+   "gpu_power_limit": 280.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 414.037109375,
+   "gpu_pcie_tx_mb": 303.36328125,
+   "cpu": 35.1,
+   "ram_used": 43772702720,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.6087260569540994,
+   "disk_write_mb": 0.20539836277592313,
+   "tok_s": 97.29124144311484,
+   "tok_s_mean": 96.62332449971758
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090",
+   "gpu_count": 1,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    1,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    99,
+    100,
+    100,
+    96,
+    100,
+    99,
+    100,
+    99,
+    99,
+    100,
+    100,
+    88,
+    0,
+    100,
+    99,
+    100,
+    99,
+    100,
+    98,
+    99,
+    99,
+    100,
+    99,
+    100,
+    81,
+    99,
+    100,
+    100,
+    99,
+    100,
+    99,
+    17,
+    99,
+    100,
+    99,
+    99,
+    99,
+    96
+   ],
+   "gpu_mem_used": [
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25382813696,
+    25407979520,
+    25418465280,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25424756736,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488,
+    25531711488
+   ],
+   "gpu_temp": [
+    43,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    42,
+    46,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    46,
+    44,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    47,
+    48,
+    47,
+    45,
+    47,
+    47,
+    47,
+    48,
+    48,
+    48,
+    46,
+    47,
+    48,
+    48,
+    48,
+    48,
+    47
+   ],
+   "gpu_power": [
+    148.8,
+    140.48,
+    132.59,
+    119.03,
+    118.99,
+    119.03,
+    119.04,
+    119.03,
+    119.12,
+    119.17,
+    119.16,
+    119.15,
+    119.26,
+    191.57,
+    276.49,
+    276.88,
+    275.95,
+    277.04,
+    277.35,
+    267.91,
+    275.37,
+    276.16,
+    278.28,
+    279.07,
+    220.36,
+    189.89,
+    258.72,
+    276.75,
+    276.67,
+    277.52,
+    275.34,
+    268.93,
+    277.69,
+    277.77,
+    276.91,
+    278.53,
+    278.56,
+    256.11,
+    199.6,
+    275.35,
+    275.49,
+    276.31,
+    275.46,
+    277.78,
+    266.35,
+    267.73,
+    276.71,
+    276.41,
+    275.34,
+    278.17,
+    245.4
+   ],
+   "gpu_pcie_rx_mb": [
+    0.33,
+    0.33,
+    0.29,
+    0.29,
+    0.33,
+    0.33,
+    0.33,
+    0.29,
+    0.33,
+    0.29,
+    0.33,
+    0.29,
+    385.14,
+    19.88,
+    1892.23,
+    13280.39,
+    85.45,
+    16838.55,
+    680.06,
+    1060.72,
+    13.45,
+    15.74,
+    5013.75,
+    1194.52,
+    0.29,
+    2531.19,
+    14.02,
+    3715.09,
+    10.68,
+    13440.37,
+    8568.48,
+    14.92,
+    15.31,
+    15.69,
+    6486.56,
+    17.31,
+    9674.45,
+    9.77,
+    2795.22,
+    4473.69,
+    14.5,
+    12.97,
+    14.92,
+    7716.66,
+    2819.78,
+    4278.33,
+    12009.48,
+    17.07,
+    9916.78,
+    8518.17,
+    414.04
+   ],
+   "cpu": [
+    0.0,
+    0.7,
+    7.3,
+    15.7,
+    7.1,
+    2.0,
+    1.2,
+    2.0,
+    2.1,
+    1.6,
+    1.9,
+    7.4,
+    13.9,
+    18.3,
+    6.1,
+    6.0,
+    16.7,
+    24.9,
+    13.2,
+    12.0,
+    7.1,
+    6.2,
+    6.0,
+    8.8,
+    81.3,
+    4.2,
+    6.8,
+    6.4,
+    7.6,
+    5.5,
+    6.0,
+    20.6,
+    12.9,
+    6.2,
+    7.0,
+    5.7,
+    5.9,
+    46.1,
+    4.0,
+    6.9,
+    5.7,
+    6.2,
+    7.1,
+    5.5,
+    5.6,
+    9.9,
+    13.7,
+    8.4,
+    7.7,
+    6.4,
+    35.1
+   ],
+   "ram_used": [
+    43381886976,
+    43381694464,
+    43410796544,
+    43434872832,
+    43483377664,
+    43485900800,
+    43484897280,
+    43481210880,
+    43469135872,
+    43462295552,
+    43458363392,
+    43496140800,
+    43624353792,
+    43648593920,
+    43633405952,
+    43641139200,
+    43635249152,
+    43689267200,
+    43846070272,
+    43924541440,
+    43924467712,
+    43918565376,
+    43883311104,
+    44002877440,
+    43964985344,
+    43959267328,
+    43943862272,
+    43937861632,
+    43930320896,
+    43922284544,
+    43915001856,
+    43817238528,
+    43819147264,
+    43818729472,
+    43828027392,
+    43824201728,
+    43825434624,
+    43872071680,
+    43734614016,
+    43728027648,
+    43719413760,
+    43703148544,
+    43695366144,
+    43687342080,
+    43744829440,
+    43791024128,
+    43789787136,
+    43766198272,
+    43761831936,
+    43750072320,
+    43772702720
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.01,
+    0.0,
+    0.0,
+    0.0,
+    25.43,
+    204.93,
+    214.14,
+    7.41,
+    0.22,
+    184.19,
+    135.03,
+    0.0,
+    101.27,
+    0.0,
+    0.0,
+    0.0,
+    0.78,
+    2.91,
+    0.61,
+    0.0,
+    0.0,
+    0.02,
+    0.0,
+    0.0,
+    79.64,
+    41.92,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    1.62,
+    0.72,
+    0.0,
+    0.0,
+    0.05,
+    0.0,
+    0.0,
+    0.18,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.61
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    97.29
+   ]
+  },
+  "time": 1790716309.6464093
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K18/speed-32k-1.json

@@ -0,0 +1,423 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K18",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 1,
+ "run_id": "052cbcbb7af7",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:21:48",
+ "prompt_tokens": 28313,
+ "completion_tokens": 57,
+ "ttft_s": 12.346,
+ "e2e_s": 12.991,
+ "api_prompt_tps": 2293.3,
+ "api_decode_tps": 86.9,
+ "engine_prompt_tps": 2324.6,
+ "engine_decode_tps": 83.1,
+ "log_lines": [
+  "strata serve: prompt 28313 tokens = 0 reused + 28313 read in 12180 ms (2324.6 tok/s), 57 generated in 686 ms (83.1 tok/s), drafts accepted 39 of 41, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 99.7% (28717 hits / 28800 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what's there and identify the last file.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 4608,
+   "expert_cache_mib": 8437,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 9557,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790716909.0337873,
+    "duration_s": 12.9,
+    "finish": "stop",
+    "prompt_tokens": 28313,
+    "reused": 0,
+    "output_tokens": 57,
+    "engine_generated": 57,
+    "prompt_ms": 12179.9,
+    "decode_ms": 685.7,
+    "decode_tok_s": 83.1,
+    "hit_rate": 0.997
+   }
+  ],
+  "requests_kept": 1,
+  "totals": {
+   "since": 1790716889.8200681,
+   "requests": 1,
+   "prompt_tokens": 28313,
+   "reused": 0,
+   "output_tokens": 57,
+   "prompt_ms": 12179.9,
+   "decode_ms": 685.7
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 0,
+     "mem_used": 15823994880,
+     "mem_total": 25769803776,
+     "temp": 44,
+     "power": 161.267
+    },
+    {
+     "index": 1,
+     "util": 90,
+     "mem_used": 24208408576,
+     "mem_total": 25769803776,
+     "temp": 51,
+     "power": 278.413
+    }
+   ],
+   "gpu_util": 45.0,
+   "gpu_mem_used": 40032403456,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 51,
+   "gpu_power": 439.68,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 5.33984375,
+   "gpu_pcie_tx_mb": 18.5009765625,
+   "cpu": 16.1,
+   "ram_used": 44574941184,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.9737281407762519,
+   "disk_write_mb": 0.11497896865254635,
+   "tok_s": 36.0,
+   "tok_s_mean": 64.01736582189179
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.5,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    41.5,
+    68.0,
+    50.0,
+    73.0,
+    87.5,
+    41.5,
+    47.0,
+    50.0,
+    78.0,
+    50.5,
+    45.0
+   ],
+   "gpu_mem_used": [
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39866728448,
+    39965294592,
+    39965294592,
+    39965294592,
+    39965294592,
+    39965294592,
+    39965294592,
+    39965294592,
+    39965294592,
+    39965294592,
+    39965294592,
+    40032403456
+   ],
+   "gpu_temp": [
+    45,
+    44,
+    44,
+    44,
+    44,
+    44,
+    45,
+    44,
+    44,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    42,
+    41,
+    41,
+    47,
+    50,
+    51,
+    51,
+    51,
+    52,
+    51,
+    52,
+    51,
+    52,
+    51
+   ],
+   "gpu_power": [
+    255.0,
+    240.14,
+    239.41,
+    239.38,
+    239.55,
+    239.75,
+    239.74,
+    239.65,
+    239.56,
+    239.63,
+    239.71,
+    239.58,
+    239.49,
+    239.62,
+    239.83,
+    239.9,
+    200.58,
+    138.26,
+    69.98,
+    230.69,
+    516.11,
+    485.77,
+    500.33,
+    518.82,
+    491.98,
+    467.22,
+    490.75,
+    506.65,
+    510.68,
+    439.68
+   ],
+   "gpu_pcie_rx_mb": [
+    0.71,
+    0.62,
+    0.67,
+    0.67,
+    0.67,
+    0.57,
+    0.71,
+    0.62,
+    0.62,
+    0.57,
+    0.67,
+    0.62,
+    0.71,
+    0.67,
+    0.67,
+    0.62,
+    0.76,
+    0.86,
+    0.71,
+    1243.59,
+    45.3,
+    2454.38,
+    77.06,
+    3382.78,
+    1099.87,
+    47.06,
+    2677.87,
+    79.25,
+    1143.26,
+    5.34
+   ],
+   "cpu": [
+    0.0,
+    1.0,
+    2.8,
+    3.4,
+    1.0,
+    1.6,
+    1.6,
+    1.0,
+    1.4,
+    0.7,
+    3.6,
+    8.3,
+    1.0,
+    8.2,
+    5.7,
+    2.6,
+    3.4,
+    1.4,
+    10.1,
+    12.9,
+    8.2,
+    10.3,
+    10.7,
+    11.6,
+    27.0,
+    14.9,
+    11.2,
+    18.3,
+    15.0,
+    16.1
+   ],
+   "ram_used": [
+    43962929152,
+    43965493248,
+    43981484032,
+    43968327680,
+    43968602112,
+    43968954368,
+    43964538880,
+    43964022784,
+    43964801024,
+    43964657664,
+    43961843712,
+    43958075392,
+    43958878208,
+    43967004672,
+    43967807488,
+    43951247360,
+    43945017344,
+    43945320448,
+    43971616768,
+    44103409664,
+    44112924672,
+    44112818176,
+    43979321344,
+    43978510336,
+    44145692672,
+    44276580352,
+    44275351552,
+    44327723008,
+    44296556544,
+    44574941184
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    64.21,
+    105.78,
+    24.45,
+    89.11,
+    67.32,
+    92.34,
+    145.4,
+    79.43,
+    98.92,
+    75.23,
+    0.0,
+    0.97
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    36.0
+   ]
+  },
+  "time": 1790716922.4098496
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K22/speed-32k-1.json

@@ -0,0 +1,270 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K22",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 1,
+ "run_id": "69d919ce1297",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:32:53",
+ "prompt_tokens": 28316,
+ "completion_tokens": 57,
+ "ttft_s": 10.575,
+ "e2e_s": 11.256,
+ "api_prompt_tps": 2677.7,
+ "api_decode_tps": 82.2,
+ "engine_prompt_tps": 2718.9,
+ "engine_decode_tps": 79.8,
+ "log_lines": [
+  "strata serve: prompt 28316 tokens = 0 reused + 28316 read in 10414 ms (2718.9 tok/s), 57 generated in 715 ms (79.8 tok/s), drafts accepted 37 of 48, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (34080 hits / 34080 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what's there and identify the last file.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 5632,
+   "expert_cache_mib": 10325,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 7669,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717573.1737459,
+    "duration_s": 11.1,
+    "finish": "stop",
+    "prompt_tokens": 28316,
+    "reused": 0,
+    "output_tokens": 57,
+    "engine_generated": 57,
+    "prompt_ms": 10414.4,
+    "decode_ms": 714.5,
+    "decode_tok_s": 79.8,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 1,
+  "totals": {
+   "since": 1790717571.262619,
+   "requests": 1,
+   "prompt_tokens": 28316,
+   "reused": 0,
+   "output_tokens": 57,
+   "prompt_ms": 10414.4,
+   "decode_ms": 714.5
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 34,
+     "mem_used": 17822580736,
+     "mem_total": 25769803776,
+     "temp": 49,
+     "power": 184.581
+    },
+    {
+     "index": 1,
+     "util": 54,
+     "mem_used": 22828482560,
+     "mem_total": 25769803776,
+     "temp": 52,
+     "power": 232.993
+    }
+   ],
+   "gpu_util": 44.0,
+   "gpu_mem_used": 40651063296,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 52,
+   "gpu_power": 417.57399999999996,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 0.666015625,
+   "gpu_pcie_tx_mb": 0.953125,
+   "cpu": 6.2,
+   "ram_used": 44281556992,
+   "ram_total": 177175990272,
+   "disk_read_mb": 3.421090719626586,
+   "disk_write_mb": 0.0,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    1.0,
+    0.0,
+    0.0,
+    73.5,
+    58.5,
+    96.0,
+    57.5,
+    95.5,
+    47.5,
+    93.0,
+    58.5,
+    50.0,
+    44.0
+   ],
+   "gpu_mem_used": [
+    40449736704,
+    40449736704,
+    40449736704,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40651063296
+   ],
+   "gpu_temp": [
+    48,
+    47,
+    47,
+    50,
+    53,
+    53,
+    54,
+    53,
+    54,
+    54,
+    54,
+    54,
+    52
+   ],
+   "gpu_power": [
+    256.98,
+    244.54,
+    244.03,
+    340.49,
+    532.78,
+    528.1,
+    525.31,
+    536.01,
+    504.78,
+    526.85,
+    529.86,
+    484.8,
+    417.57
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.62,
+    0.67,
+    78.72,
+    82.54,
+    76.1,
+    85.97,
+    55.17,
+    62.23,
+    87.12,
+    83.54,
+    85.83,
+    0.67
+   ],
+   "cpu": [
+    0.0,
+    1.2,
+    5.4,
+    10.7,
+    10.0,
+    9.8,
+    14.0,
+    18.3,
+    17.8,
+    18.6,
+    9.0,
+    5.8,
+    6.2
+   ],
+   "ram_used": [
+    43564908544,
+    43556737024,
+    43564126208,
+    43739512832,
+    43734302720,
+    43734560768,
+    43735560192,
+    43898122240,
+    44013469696,
+    43991674880,
+    43978436608,
+    43974189056,
+    44281556992
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    73.94,
+    96.25,
+    39.8,
+    73.77,
+    144.08,
+    110.85,
+    127.27,
+    131.68,
+    42.81,
+    0.0,
+    3.42
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790717584.813652
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K22/speed-32k-2.json

@@ -0,0 +1,383 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K22",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 2,
+ "run_id": "8506420b91e1",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:33:04",
+ "prompt_tokens": 31633,
+ "completion_tokens": 45,
+ "ttft_s": 10.85,
+ "e2e_s": 11.271,
+ "api_prompt_tps": 2915.4,
+ "api_decode_tps": 104.6,
+ "engine_prompt_tps": 2962.7,
+ "engine_decode_tps": 103.3,
+ "log_lines": [
+  "strata serve: prompt 31633 tokens = 0 reused + 31633 read in 10677 ms (2962.7 tok/s), 45 generated in 436 ms (103.3 tok/s), drafts accepted 32 of 37, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (24960 hits / 24960 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what the last file does.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 5632,
+   "expert_cache_mib": 10325,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 7669,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717584.9637764,
+    "duration_s": 11.1,
+    "finish": "stop",
+    "prompt_tokens": 31633,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 10677.2,
+    "decode_ms": 435.6,
+    "decode_tok_s": 103.3,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717573.1737459,
+    "duration_s": 11.1,
+    "finish": "stop",
+    "prompt_tokens": 28316,
+    "reused": 0,
+    "output_tokens": 57,
+    "engine_generated": 57,
+    "prompt_ms": 10414.4,
+    "decode_ms": 714.5,
+    "decode_tok_s": 79.8,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 2,
+  "totals": {
+   "since": 1790717571.262619,
+   "requests": 2,
+   "prompt_tokens": 59949,
+   "reused": 0,
+   "output_tokens": 102,
+   "prompt_ms": 21091.6,
+   "decode_ms": 1150.1
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 37,
+     "mem_used": 17822580736,
+     "mem_total": 25769803776,
+     "temp": 49,
+     "power": 187.064
+    },
+    {
+     "index": 1,
+     "util": 60,
+     "mem_used": 22828482560,
+     "mem_total": 25769803776,
+     "temp": 53,
+     "power": 243.674
+    }
+   ],
+   "gpu_util": 48.5,
+   "gpu_mem_used": 40651063296,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 53,
+   "gpu_power": 430.738,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 0.6181640625,
+   "gpu_pcie_tx_mb": 1.0,
+   "cpu": 6.1,
+   "ram_used": 44308209664,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.7959400039611647,
+   "disk_write_mb": 0.24130307812397303,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    1.0,
+    0.0,
+    0.0,
+    73.5,
+    58.5,
+    96.0,
+    57.5,
+    95.5,
+    47.5,
+    93.0,
+    58.5,
+    50.0,
+    44.0,
+    18.0,
+    52.0,
+    95.5,
+    50.0,
+    97.0,
+    24.5,
+    95.5,
+    82.0,
+    96.5,
+    50.0,
+    48.5
+   ],
+   "gpu_mem_used": [
+    40449736704,
+    40449736704,
+    40449736704,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296
+   ],
+   "gpu_temp": [
+    48,
+    47,
+    47,
+    50,
+    53,
+    53,
+    54,
+    53,
+    54,
+    54,
+    54,
+    54,
+    52,
+    49,
+    54,
+    54,
+    54,
+    54,
+    52,
+    54,
+    54,
+    54,
+    54,
+    53
+   ],
+   "gpu_power": [
+    256.98,
+    244.54,
+    244.03,
+    340.49,
+    532.78,
+    528.1,
+    525.31,
+    536.01,
+    504.78,
+    526.85,
+    529.86,
+    484.8,
+    417.57,
+    353.2,
+    539.11,
+    526.73,
+    525.83,
+    531.55,
+    507.76,
+    523.24,
+    527.24,
+    526.07,
+    501.32,
+    430.74
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.62,
+    0.67,
+    78.72,
+    82.54,
+    76.1,
+    85.97,
+    55.17,
+    62.23,
+    87.12,
+    83.54,
+    85.83,
+    0.67,
+    1765.25,
+    83.88,
+    85.4,
+    85.07,
+    88.59,
+    82.35,
+    78.3,
+    85.16,
+    61.94,
+    46.3,
+    0.62
+   ],
+   "cpu": [
+    0.0,
+    1.2,
+    5.4,
+    10.7,
+    10.0,
+    9.8,
+    14.0,
+    18.3,
+    17.8,
+    18.6,
+    9.0,
+    5.8,
+    6.2,
+    4.4,
+    6.6,
+    6.4,
+    5.8,
+    6.1,
+    7.4,
+    5.9,
+    6.8,
+    19.8,
+    14.2,
+    6.1
+   ],
+   "ram_used": [
+    43564908544,
+    43556737024,
+    43564126208,
+    43739512832,
+    43734302720,
+    43734560768,
+    43735560192,
+    43898122240,
+    44013469696,
+    43991674880,
+    43978436608,
+    43974189056,
+    44281556992,
+    44278607872,
+    44263776256,
+    44251099136,
+    44242841600,
+    44235354112,
+    44232339456,
+    44218642432,
+    44210057216,
+    44216344576,
+    44288196608,
+    44308209664
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    73.94,
+    96.25,
+    39.8,
+    73.77,
+    144.08,
+    110.85,
+    127.27,
+    131.68,
+    42.81,
+    0.0,
+    3.42,
+    0.48,
+    0.01,
+    0.04,
+    0.06,
+    0.02,
+    0.02,
+    0.02,
+    12.53,
+    104.78,
+    0.0,
+    0.8
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790717596.5877995
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K22/speed-32k-3.json

@@ -0,0 +1,496 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K22",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 3,
+ "run_id": "831d87a1dacc",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:33:16",
+ "prompt_tokens": 31601,
+ "completion_tokens": 60,
+ "ttft_s": 10.877,
+ "e2e_s": 11.43,
+ "api_prompt_tps": 2905.4,
+ "api_decode_tps": 106.7,
+ "engine_prompt_tps": 2951.6,
+ "engine_decode_tps": 105.7,
+ "log_lines": [
+  "strata serve: prompt 31601 tokens = 0 reused + 31601 read in 10706 ms (2951.6 tok/s), 60 generated in 568 ms (105.7 tok/s), drafts accepted 41 of 46, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (31680 hits / 31680 lookups)"
+ ],
+ "answer_head": "I'll start by examining the repository structure to understand what the last file does.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 5632,
+   "expert_cache_mib": 10325,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 7669,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717596.735188,
+    "duration_s": 11.3,
+    "finish": "stop",
+    "prompt_tokens": 31601,
+    "reused": 0,
+    "output_tokens": 60,
+    "engine_generated": 60,
+    "prompt_ms": 10706.3,
+    "decode_ms": 567.6,
+    "decode_tok_s": 105.7,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717584.9637764,
+    "duration_s": 11.1,
+    "finish": "stop",
+    "prompt_tokens": 31633,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 10677.2,
+    "decode_ms": 435.6,
+    "decode_tok_s": 103.3,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717573.1737459,
+    "duration_s": 11.1,
+    "finish": "stop",
+    "prompt_tokens": 28316,
+    "reused": 0,
+    "output_tokens": 57,
+    "engine_generated": 57,
+    "prompt_ms": 10414.4,
+    "decode_ms": 714.5,
+    "decode_tok_s": 79.8,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 3,
+  "totals": {
+   "since": 1790717571.262619,
+   "requests": 3,
+   "prompt_tokens": 91550,
+   "reused": 0,
+   "output_tokens": 162,
+   "prompt_ms": 31797.899999999998,
+   "decode_ms": 1717.6999999999998
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 25,
+     "mem_used": 17822580736,
+     "mem_total": 25769803776,
+     "temp": 50,
+     "power": 201.214
+    },
+    {
+     "index": 1,
+     "util": 61,
+     "mem_used": 22828482560,
+     "mem_total": 25769803776,
+     "temp": 53,
+     "power": 238.993
+    }
+   ],
+   "gpu_util": 43.0,
+   "gpu_mem_used": 40651063296,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 53,
+   "gpu_power": 440.207,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 0.666015625,
+   "gpu_pcie_tx_mb": 0.9052734375,
+   "cpu": 4.4,
+   "ram_used": 44291919872,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.7281688058408962,
+   "disk_write_mb": 0.01802398034259644,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    1.0,
+    0.0,
+    0.0,
+    73.5,
+    58.5,
+    96.0,
+    57.5,
+    95.5,
+    47.5,
+    93.0,
+    58.5,
+    50.0,
+    44.0,
+    18.0,
+    52.0,
+    95.5,
+    50.0,
+    97.0,
+    24.5,
+    95.5,
+    82.0,
+    96.5,
+    50.0,
+    48.5,
+    49.5,
+    96.0,
+    48.0,
+    96.0,
+    47.5,
+    94.5,
+    61.0,
+    97.5,
+    47.5,
+    49.5,
+    43.0
+   ],
+   "gpu_mem_used": [
+    40449736704,
+    40449736704,
+    40449736704,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296,
+    40651063296
+   ],
+   "gpu_temp": [
+    48,
+    47,
+    47,
+    50,
+    53,
+    53,
+    54,
+    53,
+    54,
+    54,
+    54,
+    54,
+    52,
+    49,
+    54,
+    54,
+    54,
+    54,
+    52,
+    54,
+    54,
+    54,
+    54,
+    53,
+    50,
+    54,
+    54,
+    54,
+    55,
+    54,
+    54,
+    54,
+    55,
+    55,
+    53
+   ],
+   "gpu_power": [
+    256.98,
+    244.54,
+    244.03,
+    340.49,
+    532.78,
+    528.1,
+    525.31,
+    536.01,
+    504.78,
+    526.85,
+    529.86,
+    484.8,
+    417.57,
+    353.2,
+    539.11,
+    526.73,
+    525.83,
+    531.55,
+    507.76,
+    523.24,
+    527.24,
+    526.07,
+    501.32,
+    430.74,
+    359.38,
+    510.67,
+    527.45,
+    526.85,
+    532.56,
+    501.47,
+    534.58,
+    526.16,
+    522.92,
+    475.95,
+    440.21
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.62,
+    0.67,
+    78.72,
+    82.54,
+    76.1,
+    85.97,
+    55.17,
+    62.23,
+    87.12,
+    83.54,
+    85.83,
+    0.67,
+    1765.25,
+    83.88,
+    85.4,
+    85.07,
+    88.59,
+    82.35,
+    78.3,
+    85.16,
+    61.94,
+    46.3,
+    0.62,
+    87.45,
+    41.53,
+    89.07,
+    84.21,
+    76.25,
+    52.17,
+    78.29,
+    83.59,
+    51.45,
+    47.92,
+    0.67
+   ],
+   "cpu": [
+    0.0,
+    1.2,
+    5.4,
+    10.7,
+    10.0,
+    9.8,
+    14.0,
+    18.3,
+    17.8,
+    18.6,
+    9.0,
+    5.8,
+    6.2,
+    4.4,
+    6.6,
+    6.4,
+    5.8,
+    6.1,
+    7.4,
+    5.9,
+    6.8,
+    19.8,
+    14.2,
+    6.1,
+    7.3,
+    6.6,
+    6.3,
+    5.7,
+    6.0,
+    6.2,
+    6.3,
+    6.1,
+    7.3,
+    6.4,
+    4.4
+   ],
+   "ram_used": [
+    43564908544,
+    43556737024,
+    43564126208,
+    43739512832,
+    43734302720,
+    43734560768,
+    43735560192,
+    43898122240,
+    44013469696,
+    43991674880,
+    43978436608,
+    43974189056,
+    44281556992,
+    44278607872,
+    44263776256,
+    44251099136,
+    44242841600,
+    44235354112,
+    44232339456,
+    44218642432,
+    44210057216,
+    44216344576,
+    44288196608,
+    44308209664,
+    44011671552,
+    43989819392,
+    43978940416,
+    43970682880,
+    43962933248,
+    44045533184,
+    44039798784,
+    44039798784,
+    44047568896,
+    44044705792,
+    44291919872
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    73.94,
+    96.25,
+    39.8,
+    73.77,
+    144.08,
+    110.85,
+    127.27,
+    131.68,
+    42.81,
+    0.0,
+    3.42,
+    0.48,
+    0.01,
+    0.04,
+    0.06,
+    0.02,
+    0.02,
+    0.02,
+    12.53,
+    104.78,
+    0.0,
+    0.8,
+    0.61,
+    0.05,
+    0.03,
+    0.09,
+    0.08,
+    0.04,
+    0.05,
+    0.04,
+    0.15,
+    0.0,
+    0.73
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790717608.5200934
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K24/speed-32k-1.json

@@ -0,0 +1,279 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K24",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 1,
+ "run_id": "87af67edfd2d",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:34:02",
+ "prompt_tokens": 28314,
+ "completion_tokens": 256,
+ "ttft_s": 10.029,
+ "e2e_s": 12.977,
+ "api_prompt_tps": 2823.1,
+ "api_decode_tps": 86.5,
+ "engine_prompt_tps": 2871.1,
+ "engine_decode_tps": 85.9,
+ "log_lines": [
+  "strata serve: prompt 28314 tokens = 0 reused + 28314 read in 9862 ms (2871.1 tok/s), 256 generated in 2981 ms (85.9 tok/s), drafts accepted 143 of 193, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (147360 hits / 147360 lookups)"
+ ],
+ "answer_head": "Looking at the last file above, `docs/AMD_HIP_PERFORMANCE.md`, it documents the performance evidence and correctness limits for the experimental AMD HIP backend targeting gfx1100 (RX 7900 XTX). It records:\n\n- The exact build/runtime configuration used for the benchmark (env vars, CLI flags, model pa",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 6144,
+   "expert_cache_mib": 11337,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 6657,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717642.434618,
+    "duration_s": 12.9,
+    "finish": "length",
+    "prompt_tokens": 28314,
+    "reused": 0,
+    "output_tokens": 256,
+    "engine_generated": 256,
+    "prompt_ms": 9861.8,
+    "decode_ms": 2981.5,
+    "decode_tok_s": 85.9,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 1,
+  "totals": {
+   "since": 1790717640.7776525,
+   "requests": 1,
+   "prompt_tokens": 28314,
+   "reused": 0,
+   "output_tokens": 256,
+   "prompt_ms": 9861.8,
+   "decode_ms": 2981.5
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 43,
+     "mem_used": 18898419712,
+     "mem_total": 25769803776,
+     "temp": 50,
+     "power": 244.874
+    },
+    {
+     "index": 1,
+     "util": 57,
+     "mem_used": 21758935040,
+     "mem_total": 25769803776,
+     "temp": 54,
+     "power": 254.71
+    }
+   ],
+   "gpu_util": 50.0,
+   "gpu_mem_used": 40657354752,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 54,
+   "gpu_power": 499.584,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 5.38671875,
+   "gpu_pcie_tx_mb": 87.7373046875,
+   "cpu": 11.7,
+   "ram_used": 44619116544,
+   "ram_total": 177175990272,
+   "disk_read_mb": 4.515214018548113,
+   "disk_write_mb": 0.17657261525048487,
+   "tok_s": 107.09643367230112,
+   "tok_s_mean": 83.26979350665239
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    1.0,
+    0.0,
+    1.0,
+    93.0,
+    94.0,
+    64.0,
+    94.5,
+    88.5,
+    95.5,
+    92.5,
+    48.5,
+    32.0,
+    48.0,
+    50.0
+   ],
+   "gpu_mem_used": [
+    40447639552,
+    40447639552,
+    40476999680,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40657354752,
+    40657354752,
+    40657354752
+   ],
+   "gpu_temp": [
+    49,
+    49,
+    49,
+    53,
+    54,
+    54,
+    55,
+    54,
+    55,
+    55,
+    55,
+    52,
+    54,
+    54
+   ],
+   "gpu_power": [
+    259.59,
+    247.18,
+    245.88,
+    414.53,
+    546.71,
+    547.76,
+    546.95,
+    533.57,
+    531.41,
+    545.46,
+    539.14,
+    402.04,
+    486.67,
+    499.58
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.62,
+    247.86,
+    81.11,
+    78.2,
+    80.92,
+    83.88,
+    57.6,
+    82.87,
+    79.92,
+    40.29,
+    5.39,
+    9.77,
+    5.39
+   ],
+   "cpu": [
+    0.0,
+    1.9,
+    9.1,
+    8.8,
+    9.5,
+    10.7,
+    13.9,
+    10.5,
+    13.9,
+    11.8,
+    6.0,
+    6.3,
+    12.4,
+    11.7
+   ],
+   "ram_used": [
+    43887411200,
+    43859918848,
+    43956232192,
+    44034678784,
+    44030210048,
+    44028076032,
+    44015280128,
+    44252610560,
+    44247789568,
+    44243210240,
+    44230340608,
+    44558966784,
+    44619108352,
+    44619116544
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    126.09,
+    44.05,
+    80.0,
+    93.94,
+    138.6,
+    104.01,
+    156.43,
+    97.38,
+    0.0,
+    1.76,
+    4.66,
+    4.52
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    78.74,
+    81.4,
+    107.1
+   ]
+  },
+  "time": 1790717655.7892108
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K24/speed-32k-2.json

@@ -0,0 +1,392 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K24",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 2,
+ "run_id": "b38394f620b3",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:34:15",
+ "prompt_tokens": 31635,
+ "completion_tokens": 45,
+ "ttft_s": 10.269,
+ "e2e_s": 10.686,
+ "api_prompt_tps": 3080.5,
+ "api_decode_tps": 105.5,
+ "engine_prompt_tps": 3130.4,
+ "engine_decode_tps": 104.2,
+ "log_lines": [
+  "strata serve: prompt 31635 tokens = 0 reused + 31635 read in 10106 ms (3130.4 tok/s), 45 generated in 432 ms (104.2 tok/s), drafts accepted 33 of 37, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (24480 hits / 24480 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what we're working with.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 6144,
+   "expert_cache_mib": 11337,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 6657,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717655.9301767,
+    "duration_s": 10.5,
+    "finish": "stop",
+    "prompt_tokens": 31635,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 10105.9,
+    "decode_ms": 431.8,
+    "decode_tok_s": 104.2,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717642.434618,
+    "duration_s": 12.9,
+    "finish": "length",
+    "prompt_tokens": 28314,
+    "reused": 0,
+    "output_tokens": 256,
+    "engine_generated": 256,
+    "prompt_ms": 9861.8,
+    "decode_ms": 2981.5,
+    "decode_tok_s": 85.9,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 2,
+  "totals": {
+   "since": 1790717640.7776525,
+   "requests": 2,
+   "prompt_tokens": 59949,
+   "reused": 0,
+   "output_tokens": 301,
+   "prompt_ms": 19967.699999999997,
+   "decode_ms": 3413.3
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 20,
+     "mem_used": 18898419712,
+     "mem_total": 25769803776,
+     "temp": 50,
+     "power": 191.174
+    },
+    {
+     "index": 1,
+     "util": 53,
+     "mem_used": 21758935040,
+     "mem_total": 25769803776,
+     "temp": 54,
+     "power": 238.032
+    }
+   ],
+   "gpu_util": 36.5,
+   "gpu_mem_used": 40657354752,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 54,
+   "gpu_power": 429.206,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 0.6181640625,
+   "gpu_pcie_tx_mb": 0.857421875,
+   "cpu": 5.3,
+   "ram_used": 44575621120,
+   "ram_total": 177175990272,
+   "disk_read_mb": 2.4688909410966033,
+   "disk_write_mb": 0.23427432287777988,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    1.0,
+    0.0,
+    1.0,
+    93.0,
+    94.0,
+    64.0,
+    94.5,
+    88.5,
+    95.5,
+    92.5,
+    48.5,
+    32.0,
+    48.0,
+    50.0,
+    0.0,
+    84.5,
+    96.0,
+    95.5,
+    79.0,
+    97.5,
+    97.0,
+    95.5,
+    96.0,
+    50.0,
+    36.5
+   ],
+   "gpu_mem_used": [
+    40447639552,
+    40447639552,
+    40476999680,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752
+   ],
+   "gpu_temp": [
+    49,
+    49,
+    49,
+    53,
+    54,
+    54,
+    55,
+    54,
+    55,
+    55,
+    55,
+    52,
+    54,
+    54,
+    50,
+    54,
+    55,
+    55,
+    55,
+    55,
+    55,
+    55,
+    55,
+    55,
+    54
+   ],
+   "gpu_power": [
+    259.59,
+    247.18,
+    245.88,
+    414.53,
+    546.71,
+    547.76,
+    546.95,
+    533.57,
+    531.41,
+    545.46,
+    539.14,
+    402.04,
+    486.67,
+    499.58,
+    409.59,
+    480.21,
+    551.08,
+    548.0,
+    547.82,
+    539.97,
+    537.72,
+    548.44,
+    548.33,
+    513.55,
+    429.21
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.62,
+    247.86,
+    81.11,
+    78.2,
+    80.92,
+    83.88,
+    57.6,
+    82.87,
+    79.92,
+    40.29,
+    5.39,
+    9.77,
+    5.39,
+    45.78,
+    64.8,
+    1284.55,
+    129.94,
+    83.06,
+    82.63,
+    84.78,
+    73.15,
+    82.44,
+    0.57,
+    0.62
+   ],
+   "cpu": [
+    0.0,
+    1.9,
+    9.1,
+    8.8,
+    9.5,
+    10.7,
+    13.9,
+    10.5,
+    13.9,
+    11.8,
+    6.0,
+    6.3,
+    12.4,
+    11.7,
+    6.7,
+    8.3,
+    6.5,
+    7.2,
+    6.1,
+    6.0,
+    6.1,
+    6.5,
+    11.2,
+    8.0,
+    5.3
+   ],
+   "ram_used": [
+    43887411200,
+    43859918848,
+    43956232192,
+    44034678784,
+    44030210048,
+    44028076032,
+    44015280128,
+    44252610560,
+    44247789568,
+    44243210240,
+    44230340608,
+    44558966784,
+    44619108352,
+    44619116544,
+    44154675200,
+    44152926208,
+    44151242752,
+    44149854208,
+    44145594368,
+    44375150592,
+    44366180352,
+    44365656064,
+    44362940416,
+    44400578560,
+    44575621120
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    126.09,
+    44.05,
+    80.0,
+    93.94,
+    138.6,
+    104.01,
+    156.43,
+    97.38,
+    0.0,
+    1.76,
+    4.66,
+    4.52,
+    0.63,
+    0.02,
+    0.04,
+    0.03,
+    0.05,
+    0.03,
+    0.02,
+    13.87,
+    103.6,
+    0.0,
+    2.47
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    78.74,
+    81.4,
+    107.1,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790717666.9788535
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K24/speed-32k-3.json

@@ -0,0 +1,496 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K24",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 3,
+ "run_id": "3bee1c1e482a",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:34:26",
+ "prompt_tokens": 31602,
+ "completion_tokens": 60,
+ "ttft_s": 10.281,
+ "e2e_s": 10.865,
+ "api_prompt_tps": 3073.8,
+ "api_decode_tps": 101.0,
+ "engine_prompt_tps": 3123.2,
+ "engine_decode_tps": 100.2,
+ "log_lines": [
+  "strata serve: prompt 31602 tokens = 0 reused + 31602 read in 10118 ms (3123.2 tok/s), 60 generated in 599 ms (100.2 tok/s), drafts accepted 40 of 52, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (34560 hits / 34560 lookups)"
+ ],
+ "answer_head": "I'll start by examining the repository structure to understand what the last file does.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 6144,
+   "expert_cache_mib": 11337,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 6657,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717667.1193056,
+    "duration_s": 10.7,
+    "finish": "stop",
+    "prompt_tokens": 31602,
+    "reused": 0,
+    "output_tokens": 60,
+    "engine_generated": 60,
+    "prompt_ms": 10118.5,
+    "decode_ms": 599.0,
+    "decode_tok_s": 100.2,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717655.9301767,
+    "duration_s": 10.5,
+    "finish": "stop",
+    "prompt_tokens": 31635,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 10105.9,
+    "decode_ms": 431.8,
+    "decode_tok_s": 104.2,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717642.434618,
+    "duration_s": 12.9,
+    "finish": "length",
+    "prompt_tokens": 28314,
+    "reused": 0,
+    "output_tokens": 256,
+    "engine_generated": 256,
+    "prompt_ms": 9861.8,
+    "decode_ms": 2981.5,
+    "decode_tok_s": 85.9,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 3,
+  "totals": {
+   "since": 1790717640.7776525,
+   "requests": 3,
+   "prompt_tokens": 91551,
+   "reused": 0,
+   "output_tokens": 361,
+   "prompt_ms": 30086.199999999997,
+   "decode_ms": 4012.3
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 43,
+     "mem_used": 18898419712,
+     "mem_total": 25769803776,
+     "temp": 51,
+     "power": 178.691
+    },
+    {
+     "index": 1,
+     "util": 51,
+     "mem_used": 21758935040,
+     "mem_total": 25769803776,
+     "temp": 54,
+     "power": 244.501
+    }
+   ],
+   "gpu_util": 47.0,
+   "gpu_mem_used": 40657354752,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 54,
+   "gpu_power": 423.192,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 5.1962890625,
+   "gpu_pcie_tx_mb": 103.138671875,
+   "cpu": 6.6,
+   "ram_used": 44596383744,
+   "ram_total": 177175990272,
+   "disk_read_mb": 1.1207609014346964,
+   "disk_write_mb": 0.0288298624163266,
+   "tok_s": 110.47676922161895,
+   "tok_s_mean": 99.0096070780873
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    1.0,
+    0.0,
+    1.0,
+    93.0,
+    94.0,
+    64.0,
+    94.5,
+    88.5,
+    95.5,
+    92.5,
+    48.5,
+    32.0,
+    48.0,
+    50.0,
+    0.0,
+    84.5,
+    96.0,
+    95.5,
+    79.0,
+    97.5,
+    97.0,
+    95.5,
+    96.0,
+    50.0,
+    36.5,
+    49.5,
+    96.5,
+    61.0,
+    94.5,
+    91.0,
+    97.0,
+    95.5,
+    98.5,
+    47.5,
+    47.0
+   ],
+   "gpu_mem_used": [
+    40447639552,
+    40447639552,
+    40476999680,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40546205696,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752,
+    40657354752
+   ],
+   "gpu_temp": [
+    49,
+    49,
+    49,
+    53,
+    54,
+    54,
+    55,
+    54,
+    55,
+    55,
+    55,
+    52,
+    54,
+    54,
+    50,
+    54,
+    55,
+    55,
+    55,
+    55,
+    55,
+    55,
+    55,
+    55,
+    54,
+    52,
+    55,
+    55,
+    55,
+    55,
+    56,
+    56,
+    55,
+    56,
+    54
+   ],
+   "gpu_power": [
+    259.59,
+    247.18,
+    245.88,
+    414.53,
+    546.71,
+    547.76,
+    546.95,
+    533.57,
+    531.41,
+    545.46,
+    539.14,
+    402.04,
+    486.67,
+    499.58,
+    409.59,
+    480.21,
+    551.08,
+    548.0,
+    547.82,
+    539.97,
+    537.72,
+    548.44,
+    548.33,
+    513.55,
+    429.21,
+    354.61,
+    553.75,
+    546.57,
+    547.59,
+    532.21,
+    535.5,
+    547.28,
+    548.49,
+    534.02,
+    423.19
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.62,
+    247.86,
+    81.11,
+    78.2,
+    80.92,
+    83.88,
+    57.6,
+    82.87,
+    79.92,
+    40.29,
+    5.39,
+    9.77,
+    5.39,
+    45.78,
+    64.8,
+    1284.55,
+    129.94,
+    83.06,
+    82.63,
+    84.78,
+    73.15,
+    82.44,
+    0.57,
+    0.62,
+    81.82,
+    83.45,
+    75.34,
+    84.16,
+    82.11,
+    81.49,
+    70.95,
+    73.91,
+    52.55,
+    5.2
+   ],
+   "cpu": [
+    0.0,
+    1.9,
+    9.1,
+    8.8,
+    9.5,
+    10.7,
+    13.9,
+    10.5,
+    13.9,
+    11.8,
+    6.0,
+    6.3,
+    12.4,
+    11.7,
+    6.7,
+    8.3,
+    6.5,
+    7.2,
+    6.1,
+    6.0,
+    6.1,
+    6.5,
+    11.2,
+    8.0,
+    5.3,
+    6.7,
+    12.7,
+    10.0,
+    5.9,
+    6.4,
+    6.0,
+    7.1,
+    5.7,
+    6.8,
+    6.6
+   ],
+   "ram_used": [
+    43887411200,
+    43859918848,
+    43956232192,
+    44034678784,
+    44030210048,
+    44028076032,
+    44015280128,
+    44252610560,
+    44247789568,
+    44243210240,
+    44230340608,
+    44558966784,
+    44619108352,
+    44619116544,
+    44154675200,
+    44152926208,
+    44151242752,
+    44149854208,
+    44145594368,
+    44375150592,
+    44366180352,
+    44365656064,
+    44362940416,
+    44400578560,
+    44575621120,
+    44112637952,
+    44134821888,
+    44114948096,
+    44112486400,
+    44240445440,
+    44343197696,
+    44341800960,
+    44344549376,
+    44344029184,
+    44596383744
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    126.09,
+    44.05,
+    80.0,
+    93.94,
+    138.6,
+    104.01,
+    156.43,
+    97.38,
+    0.0,
+    1.76,
+    4.66,
+    4.52,
+    0.63,
+    0.02,
+    0.04,
+    0.03,
+    0.05,
+    0.03,
+    0.02,
+    13.87,
+    103.6,
+    0.0,
+    2.47,
+    0.63,
+    0.05,
+    0.08,
+    0.08,
+    0.04,
+    0.07,
+    0.04,
+    0.17,
+    0.0,
+    1.12
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    78.74,
+    81.4,
+    107.1,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    110.48
+   ]
+  },
+  "time": 1790717678.3471994
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K26/speed-32k-1.json

@@ -0,0 +1,261 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K26",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 1,
+ "run_id": "5ca39dba7489",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:35:22",
+ "prompt_tokens": 28314,
+ "completion_tokens": 48,
+ "ttft_s": 9.79,
+ "e2e_s": 10.297,
+ "api_prompt_tps": 2892.2,
+ "api_decode_tps": 92.7,
+ "engine_prompt_tps": 2940.2,
+ "engine_decode_tps": 88.8,
+ "log_lines": [
+  "strata serve: prompt 28314 tokens = 0 reused + 28314 read in 9630 ms (2940.2 tok/s), 48 generated in 540 ms (88.8 tok/s), drafts accepted 33 of 37, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (25920 hits / 25920 lookups)"
+ ],
+ "answer_head": "I'll first look at the repository structure to understand what files exist and identify the last file.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 6656,
+   "expert_cache_mib": 12387,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 5607,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717722.129571,
+    "duration_s": 10.2,
+    "finish": "stop",
+    "prompt_tokens": 28314,
+    "reused": 0,
+    "output_tokens": 48,
+    "engine_generated": 48,
+    "prompt_ms": 9630.1,
+    "decode_ms": 540.5,
+    "decode_tok_s": 88.8,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 1,
+  "totals": {
+   "since": 1790717720.412441,
+   "requests": 1,
+   "prompt_tokens": 28314,
+   "reused": 0,
+   "output_tokens": 48,
+   "prompt_ms": 9630.1,
+   "decode_ms": 540.5
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 47,
+     "mem_used": 19980550144,
+     "mem_total": 25769803776,
+     "temp": 51,
+     "power": 179.665
+    },
+    {
+     "index": 1,
+     "util": 28,
+     "mem_used": 20641153024,
+     "mem_total": 25769803776,
+     "temp": 53,
+     "power": 236.004
+    }
+   ],
+   "gpu_util": 37.5,
+   "gpu_mem_used": 40621703168,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 53,
+   "gpu_power": 415.669,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 0.666015625,
+   "gpu_pcie_tx_mb": 0.9052734375,
+   "cpu": 6.0,
+   "ram_used": 44539072512,
+   "ram_total": 177175990272,
+   "disk_read_mb": 2.97776661958663,
+   "disk_write_mb": 0.0,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.5,
+    0.0,
+    0.5,
+    71.0,
+    95.5,
+    96.0,
+    91.5,
+    66.5,
+    95.5,
+    90.5,
+    84.5,
+    37.5
+   ],
+   "gpu_mem_used": [
+    40447639552,
+    40447639552,
+    40472805376,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40621703168
+   ],
+   "gpu_temp": [
+    50,
+    50,
+    50,
+    52,
+    55,
+    55,
+    56,
+    56,
+    56,
+    55,
+    56,
+    53
+   ],
+   "gpu_power": [
+    261.03,
+    248.02,
+    247.5,
+    351.95,
+    548.48,
+    553.77,
+    555.05,
+    536.77,
+    531.38,
+    552.37,
+    551.57,
+    415.67
+   ],
+   "gpu_pcie_rx_mb": [
+    0.76,
+    0.62,
+    224.64,
+    86.02,
+    83.16,
+    75.62,
+    86.69,
+    102.66,
+    65.66,
+    83.97,
+    38.86,
+    0.67
+   ],
+   "cpu": [
+    0.0,
+    1.1,
+    8.1,
+    9.1,
+    9.3,
+    12.2,
+    12.6,
+    12.6,
+    23.5,
+    14.7,
+    5.9,
+    6.0
+   ],
+   "ram_used": [
+    43871281152,
+    43867545600,
+    43958726656,
+    44040531968,
+    44041007104,
+    44033200128,
+    44032602112,
+    44244361216,
+    44250234880,
+    44236812288,
+    44233678848,
+    44539072512
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    122.8,
+    47.19,
+    79.99,
+    100.77,
+    127.09,
+    108.72,
+    156.54,
+    97.45,
+    0.0,
+    2.98
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790717732.8116624
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K26/speed-32k-2.json

@@ -0,0 +1,365 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K26",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 2,
+ "run_id": "14c7210ce0e9",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:35:32",
+ "prompt_tokens": 31635,
+ "completion_tokens": 45,
+ "ttft_s": 10.029,
+ "e2e_s": 10.496,
+ "api_prompt_tps": 3154.3,
+ "api_decode_tps": 94.3,
+ "engine_prompt_tps": 3205.2,
+ "engine_decode_tps": 93.5,
+ "log_lines": [
+  "strata serve: prompt 31635 tokens = 0 reused + 31635 read in 9870 ms (3205.2 tok/s), 45 generated in 481 ms (93.5 tok/s), drafts accepted 31 of 36, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (25440 hits / 25440 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what the last file does.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 6656,
+   "expert_cache_mib": 12387,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 5607,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717732.947479,
+    "duration_s": 10.4,
+    "finish": "stop",
+    "prompt_tokens": 31635,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 9870.0,
+    "decode_ms": 481.3,
+    "decode_tok_s": 93.5,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717722.129571,
+    "duration_s": 10.2,
+    "finish": "stop",
+    "prompt_tokens": 28314,
+    "reused": 0,
+    "output_tokens": 48,
+    "engine_generated": 48,
+    "prompt_ms": 9630.1,
+    "decode_ms": 540.5,
+    "decode_tok_s": 88.8,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 2,
+  "totals": {
+   "since": 1790717720.412441,
+   "requests": 2,
+   "prompt_tokens": 59949,
+   "reused": 0,
+   "output_tokens": 93,
+   "prompt_ms": 19500.1,
+   "decode_ms": 1021.8
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 51,
+     "mem_used": 19991035904,
+     "mem_total": 25769803776,
+     "temp": 51,
+     "power": 190.866
+    },
+    {
+     "index": 1,
+     "util": 56,
+     "mem_used": 20653735936,
+     "mem_total": 25769803776,
+     "temp": 55,
+     "power": 249.813
+    }
+   ],
+   "gpu_util": 53.5,
+   "gpu_mem_used": 40644771840,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 55,
+   "gpu_power": 440.679,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 16.44921875,
+   "gpu_pcie_tx_mb": 82.0625,
+   "cpu": 6.0,
+   "ram_used": 44553875456,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.6053434938228842,
+   "disk_write_mb": 0.0,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.5,
+    0.0,
+    0.5,
+    71.0,
+    95.5,
+    96.0,
+    91.5,
+    66.5,
+    95.5,
+    90.5,
+    84.5,
+    37.5,
+    1.5,
+    97.0,
+    96.0,
+    81.0,
+    86.5,
+    95.5,
+    95.0,
+    96.5,
+    95.0,
+    53.5
+   ],
+   "gpu_mem_used": [
+    40447639552,
+    40447639552,
+    40472805376,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40644771840
+   ],
+   "gpu_temp": [
+    50,
+    50,
+    50,
+    52,
+    55,
+    55,
+    56,
+    56,
+    56,
+    55,
+    56,
+    53,
+    51,
+    56,
+    56,
+    56,
+    56,
+    56,
+    56,
+    56,
+    56,
+    55
+   ],
+   "gpu_power": [
+    261.03,
+    248.02,
+    247.5,
+    351.95,
+    548.48,
+    553.77,
+    555.05,
+    536.77,
+    531.38,
+    552.37,
+    551.57,
+    415.67,
+    326.37,
+    532.86,
+    555.24,
+    552.15,
+    555.12,
+    507.8,
+    554.85,
+    554.0,
+    554.13,
+    440.68
+   ],
+   "gpu_pcie_rx_mb": [
+    0.76,
+    0.62,
+    224.64,
+    86.02,
+    83.16,
+    75.62,
+    86.69,
+    102.66,
+    65.66,
+    83.97,
+    38.86,
+    0.67,
+    3698.35,
+    132.46,
+    131.89,
+    82.06,
+    85.92,
+    83.02,
+    1279.88,
+    50.4,
+    86.21,
+    16.45
+   ],
+   "cpu": [
+    0.0,
+    1.1,
+    8.1,
+    9.1,
+    9.3,
+    12.2,
+    12.6,
+    12.6,
+    23.5,
+    14.7,
+    5.9,
+    6.0,
+    4.5,
+    6.1,
+    6.0,
+    6.4,
+    6.7,
+    5.9,
+    6.7,
+    9.9,
+    7.4,
+    6.0
+   ],
+   "ram_used": [
+    43871281152,
+    43867545600,
+    43958726656,
+    44040531968,
+    44041007104,
+    44033200128,
+    44032602112,
+    44244361216,
+    44250234880,
+    44236812288,
+    44233678848,
+    44539072512,
+    44064968704,
+    44058497024,
+    44058497024,
+    44058501120,
+    44175929344,
+    44294356992,
+    44294352896,
+    44295569408,
+    44291391488,
+    44553875456
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    122.8,
+    47.19,
+    79.99,
+    100.77,
+    127.09,
+    108.72,
+    156.54,
+    97.45,
+    0.0,
+    2.98,
+    0.47,
+    0.01,
+    0.04,
+    0.06,
+    0.03,
+    0.03,
+    12.57,
+    71.85,
+    33.12,
+    0.61
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790717743.8106396
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K26/speed-32k-3.json

@@ -0,0 +1,469 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K26",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 3,
+ "run_id": "3f243fdb63ee",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:35:43",
+ "prompt_tokens": 31601,
+ "completion_tokens": 60,
+ "ttft_s": 10.026,
+ "e2e_s": 10.61,
+ "api_prompt_tps": 3151.9,
+ "api_decode_tps": 101.0,
+ "engine_prompt_tps": 3208.3,
+ "engine_decode_tps": 100.2,
+ "log_lines": [
+  "strata serve: prompt 31601 tokens = 0 reused + 31601 read in 9850 ms (3208.3 tok/s), 60 generated in 599 ms (100.2 tok/s), drafts accepted 40 of 50, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (34080 hits / 34080 lookups)"
+ ],
+ "answer_head": "I'll start by examining the repository structure to understand what the last file is.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 6656,
+   "expert_cache_mib": 12387,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 5607,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717743.964174,
+    "duration_s": 10.5,
+    "finish": "stop",
+    "prompt_tokens": 31601,
+    "reused": 0,
+    "output_tokens": 60,
+    "engine_generated": 60,
+    "prompt_ms": 9849.9,
+    "decode_ms": 598.9,
+    "decode_tok_s": 100.2,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717732.947479,
+    "duration_s": 10.4,
+    "finish": "stop",
+    "prompt_tokens": 31635,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 9870.0,
+    "decode_ms": 481.3,
+    "decode_tok_s": 93.5,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717722.129571,
+    "duration_s": 10.2,
+    "finish": "stop",
+    "prompt_tokens": 28314,
+    "reused": 0,
+    "output_tokens": 48,
+    "engine_generated": 48,
+    "prompt_ms": 9630.1,
+    "decode_ms": 540.5,
+    "decode_tok_s": 88.8,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 3,
+  "totals": {
+   "since": 1790717720.412441,
+   "requests": 3,
+   "prompt_tokens": 91550,
+   "reused": 0,
+   "output_tokens": 153,
+   "prompt_ms": 29350.0,
+   "decode_ms": 1620.6999999999998
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 46,
+     "mem_used": 19991035904,
+     "mem_total": 25769803776,
+     "temp": 52,
+     "power": 189.922
+    },
+    {
+     "index": 1,
+     "util": 52,
+     "mem_used": 20653735936,
+     "mem_total": 25769803776,
+     "temp": 55,
+     "power": 246.398
+    }
+   ],
+   "gpu_util": 49.0,
+   "gpu_mem_used": 40644771840,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 55,
+   "gpu_power": 436.32,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 17.8330078125,
+   "gpu_pcie_tx_mb": 43.1533203125,
+   "cpu": 6.0,
+   "ram_used": 44614168576,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.4973320821900814,
+   "disk_write_mb": 0.05405783502066102,
+   "tok_s": 99.26679787882165,
+   "tok_s_mean": 97.997900113756
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.5,
+    0.0,
+    0.5,
+    71.0,
+    95.5,
+    96.0,
+    91.5,
+    66.5,
+    95.5,
+    90.5,
+    84.5,
+    37.5,
+    1.5,
+    97.0,
+    96.0,
+    81.0,
+    86.5,
+    95.5,
+    95.0,
+    96.5,
+    95.0,
+    53.5,
+    0.0,
+    95.0,
+    95.5,
+    82.0,
+    94.5,
+    93.0,
+    88.5,
+    96.0,
+    97.0,
+    49.0
+   ],
+   "gpu_mem_used": [
+    40447639552,
+    40447639552,
+    40472805376,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40535719936,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40621703168,
+    40644771840,
+    40644771840,
+    40644771840,
+    40644771840,
+    40644771840,
+    40644771840,
+    40644771840,
+    40644771840,
+    40644771840,
+    40644771840,
+    40644771840
+   ],
+   "gpu_temp": [
+    50,
+    50,
+    50,
+    52,
+    55,
+    55,
+    56,
+    56,
+    56,
+    55,
+    56,
+    53,
+    51,
+    56,
+    56,
+    56,
+    56,
+    56,
+    56,
+    56,
+    56,
+    55,
+    52,
+    55,
+    56,
+    56,
+    56,
+    56,
+    56,
+    56,
+    56,
+    55
+   ],
+   "gpu_power": [
+    261.03,
+    248.02,
+    247.5,
+    351.95,
+    548.48,
+    553.77,
+    555.05,
+    536.77,
+    531.38,
+    552.37,
+    551.57,
+    415.67,
+    326.37,
+    532.86,
+    555.24,
+    552.15,
+    555.12,
+    507.8,
+    554.85,
+    554.0,
+    554.13,
+    440.68,
+    363.75,
+    474.54,
+    552.72,
+    554.16,
+    554.3,
+    509.24,
+    555.11,
+    555.88,
+    555.36,
+    436.32
+   ],
+   "gpu_pcie_rx_mb": [
+    0.76,
+    0.62,
+    224.64,
+    86.02,
+    83.16,
+    75.62,
+    86.69,
+    102.66,
+    65.66,
+    83.97,
+    38.86,
+    0.67,
+    3698.35,
+    132.46,
+    131.89,
+    82.06,
+    85.92,
+    83.02,
+    1279.88,
+    50.4,
+    86.21,
+    16.45,
+    38.96,
+    81.63,
+    83.25,
+    84.4,
+    72.53,
+    127.22,
+    48.4,
+    96.51,
+    100.71,
+    17.83
+   ],
+   "cpu": [
+    0.0,
+    1.1,
+    8.1,
+    9.1,
+    9.3,
+    12.2,
+    12.6,
+    12.6,
+    23.5,
+    14.7,
+    5.9,
+    6.0,
+    4.5,
+    6.1,
+    6.0,
+    6.4,
+    6.7,
+    5.9,
+    6.7,
+    9.9,
+    7.4,
+    6.0,
+    11.7,
+    10.8,
+    6.2,
+    11.4,
+    7.0,
+    6.7,
+    5.6,
+    5.4,
+    6.0,
+    6.0
+   ],
+   "ram_used": [
+    43871281152,
+    43867545600,
+    43958726656,
+    44040531968,
+    44041007104,
+    44033200128,
+    44032602112,
+    44244361216,
+    44250234880,
+    44236812288,
+    44233678848,
+    44539072512,
+    44064968704,
+    44058497024,
+    44058497024,
+    44058501120,
+    44175929344,
+    44294356992,
+    44294352896,
+    44295569408,
+    44291391488,
+    44553875456,
+    44129808384,
+    44180946944,
+    44184666112,
+    44182659072,
+    44296114176,
+    44404658176,
+    44394999808,
+    44386783232,
+    44374441984,
+    44614168576
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    122.8,
+    47.19,
+    79.99,
+    100.77,
+    127.09,
+    108.72,
+    156.54,
+    97.45,
+    0.0,
+    2.98,
+    0.47,
+    0.01,
+    0.04,
+    0.06,
+    0.03,
+    0.03,
+    12.57,
+    71.85,
+    33.12,
+    0.61,
+    0.53,
+    0.06,
+    0.06,
+    0.09,
+    0.08,
+    0.04,
+    0.04,
+    0.04,
+    0.15,
+    0.5
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    99.27
+   ]
+  },
+  "time": 1790717754.9239163
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K28/speed-32k-1.json

@@ -0,0 +1,261 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K28",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 1,
+ "run_id": "0796a1ce12e4",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:36:29",
+ "prompt_tokens": 28316,
+ "completion_tokens": 57,
+ "ttft_s": 10.285,
+ "e2e_s": 10.86,
+ "api_prompt_tps": 2753.1,
+ "api_decode_tps": 97.4,
+ "engine_prompt_tps": 2798.5,
+ "engine_decode_tps": 93.7,
+ "log_lines": [
+  "strata serve: prompt 28316 tokens = 0 reused + 28316 read in 10118 ms (2798.5 tok/s), 57 generated in 608 ms (93.7 tok/s), drafts accepted 40 of 42, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (28800 hits / 28800 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what's there and identify the last file.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 7168,
+   "expert_cache_mib": 13437,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 4557,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717789.1846194,
+    "duration_s": 10.7,
+    "finish": "stop",
+    "prompt_tokens": 28316,
+    "reused": 0,
+    "output_tokens": 57,
+    "engine_generated": 57,
+    "prompt_ms": 10118.2,
+    "decode_ms": 608.0,
+    "decode_tok_s": 93.8,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 1,
+  "totals": {
+   "since": 1790717787.625935,
+   "requests": 1,
+   "prompt_tokens": 28316,
+   "reused": 0,
+   "output_tokens": 57,
+   "prompt_ms": 10118.2,
+   "decode_ms": 608.0
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 41,
+     "mem_used": 21104623616,
+     "mem_total": 25769803776,
+     "temp": 52,
+     "power": 189.832
+    },
+    {
+     "index": 1,
+     "util": 42,
+     "mem_used": 19548536832,
+     "mem_total": 25769803776,
+     "temp": 54,
+     "power": 230.563
+    }
+   ],
+   "gpu_util": 41.5,
+   "gpu_mem_used": 40653160448,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 54,
+   "gpu_power": 420.395,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 17.1650390625,
+   "gpu_pcie_tx_mb": 53.119140625,
+   "cpu": 6.1,
+   "ram_used": 44503613440,
+   "ram_total": 177175990272,
+   "disk_read_mb": 1.946188226381293,
+   "disk_write_mb": 0.0036040522710764685,
+   "tok_s": 81.42212134334822,
+   "tok_s_mean": 78.79383849818437
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.5,
+    0.0,
+    0.0,
+    46.5,
+    96.0,
+    72.5,
+    93.0,
+    90.0,
+    95.5,
+    93.5,
+    97.5,
+    41.5
+   ],
+   "gpu_mem_used": [
+    40447639552,
+    40447639552,
+    40495874048,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40653160448
+   ],
+   "gpu_temp": [
+    51,
+    50,
+    50,
+    52,
+    55,
+    54,
+    56,
+    54,
+    56,
+    56,
+    57,
+    54
+   ],
+   "gpu_power": [
+    261.46,
+    249.04,
+    248.59,
+    342.07,
+    531.07,
+    533.47,
+    545.68,
+    511.29,
+    533.34,
+    534.58,
+    541.51,
+    420.39
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.62,
+    182.48,
+    55.88,
+    87.02,
+    80.58,
+    57.5,
+    78.87,
+    83.88,
+    1294.42,
+    46.78,
+    17.17
+   ],
+   "cpu": [
+    0.0,
+    6.6,
+    18.0,
+    11.3,
+    10.5,
+    9.8,
+    11.5,
+    13.9,
+    11.4,
+    12.9,
+    7.4,
+    6.1
+   ],
+   "ram_used": [
+    43799613440,
+    43777974272,
+    43950305280,
+    43962880000,
+    43939622912,
+    43930345472,
+    43932086272,
+    44071780352,
+    44183257088,
+    44182880256,
+    44179062784,
+    44503613440
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    129.59,
+    40.83,
+    79.94,
+    84.92,
+    115.02,
+    136.42,
+    117.79,
+    106.04,
+    29.9,
+    1.95
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    81.42
+   ]
+  },
+  "time": 1790717800.421838
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K28/speed-32k-2.json

@@ -0,0 +1,374 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K28",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 2,
+ "run_id": "3d5bf2c2aa6f",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:36:40",
+ "prompt_tokens": 31631,
+ "completion_tokens": 45,
+ "ttft_s": 10.58,
+ "e2e_s": 10.972,
+ "api_prompt_tps": 2989.7,
+ "api_decode_tps": 112.3,
+ "engine_prompt_tps": 3034.9,
+ "engine_decode_tps": 110.6,
+ "log_lines": [
+  "strata serve: prompt 31631 tokens = 0 reused + 31631 read in 10423 ms (3034.9 tok/s), 45 generated in 407 ms (110.6 tok/s), drafts accepted 33 of 34, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (23040 hits / 23040 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what we're working with.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 7168,
+   "expert_cache_mib": 13437,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 4557,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717800.5571585,
+    "duration_s": 10.8,
+    "finish": "stop",
+    "prompt_tokens": 31631,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 10422.5,
+    "decode_ms": 406.8,
+    "decode_tok_s": 110.6,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717789.1846194,
+    "duration_s": 10.7,
+    "finish": "stop",
+    "prompt_tokens": 28316,
+    "reused": 0,
+    "output_tokens": 57,
+    "engine_generated": 57,
+    "prompt_ms": 10118.2,
+    "decode_ms": 608.0,
+    "decode_tok_s": 93.8,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 2,
+  "totals": {
+   "since": 1790717787.625935,
+   "requests": 2,
+   "prompt_tokens": 59947,
+   "reused": 0,
+   "output_tokens": 102,
+   "prompt_ms": 20540.7,
+   "decode_ms": 1014.8
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 46,
+     "mem_used": 21104623616,
+     "mem_total": 25769803776,
+     "temp": 51,
+     "power": 204.027
+    },
+    {
+     "index": 1,
+     "util": 12,
+     "mem_used": 19548536832,
+     "mem_total": 25769803776,
+     "temp": 54,
+     "power": 226.431
+    }
+   ],
+   "gpu_util": 29.0,
+   "gpu_mem_used": 40653160448,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 54,
+   "gpu_power": 430.45799999999997,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 0.6181640625,
+   "gpu_pcie_tx_mb": 0.9052734375,
+   "cpu": 4.3,
+   "ram_used": 44573519872,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.9768799607845553,
+   "disk_write_mb": 0.0,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.5,
+    0.0,
+    0.0,
+    46.5,
+    96.0,
+    72.5,
+    93.0,
+    90.0,
+    95.5,
+    93.5,
+    97.5,
+    41.5,
+    0.0,
+    96.0,
+    93.0,
+    97.5,
+    94.5,
+    97.0,
+    95.0,
+    97.0,
+    93.5,
+    67.0,
+    29.0
+   ],
+   "gpu_mem_used": [
+    40447639552,
+    40447639552,
+    40495874048,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448
+   ],
+   "gpu_temp": [
+    51,
+    50,
+    50,
+    52,
+    55,
+    54,
+    56,
+    54,
+    56,
+    56,
+    57,
+    54,
+    52,
+    55,
+    54,
+    56,
+    56,
+    56,
+    56,
+    57,
+    57,
+    56,
+    54
+   ],
+   "gpu_power": [
+    261.46,
+    249.04,
+    248.59,
+    342.07,
+    531.07,
+    533.47,
+    545.68,
+    511.29,
+    533.34,
+    534.58,
+    541.51,
+    420.39,
+    375.37,
+    452.84,
+    528.99,
+    547.53,
+    532.29,
+    524.3,
+    518.92,
+    543.34,
+    532.25,
+    534.03,
+    430.46
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.62,
+    182.48,
+    55.88,
+    87.02,
+    80.58,
+    57.5,
+    78.87,
+    83.88,
+    1294.42,
+    46.78,
+    17.17,
+    42.15,
+    1288.27,
+    41.05,
+    75.34,
+    70.76,
+    44.15,
+    79.87,
+    61.61,
+    75.63,
+    42.06,
+    0.62
+   ],
+   "cpu": [
+    0.0,
+    6.6,
+    18.0,
+    11.3,
+    10.5,
+    9.8,
+    11.5,
+    13.9,
+    11.4,
+    12.9,
+    7.4,
+    6.1,
+    4.2,
+    6.4,
+    6.0,
+    12.9,
+    11.2,
+    6.1,
+    8.2,
+    8.8,
+    14.0,
+    6.4,
+    4.3
+   ],
+   "ram_used": [
+    43799613440,
+    43777974272,
+    43950305280,
+    43962880000,
+    43939622912,
+    43930345472,
+    43932086272,
+    44071780352,
+    44183257088,
+    44182880256,
+    44179062784,
+    44503613440,
+    44015304704,
+    44019281920,
+    44021350400,
+    44034875392,
+    44111585280,
+    44348657664,
+    44344815616,
+    44359872512,
+    44334280704,
+    44327985152,
+    44573519872
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    129.59,
+    40.83,
+    79.94,
+    84.92,
+    115.02,
+    136.42,
+    117.79,
+    106.04,
+    29.9,
+    1.95,
+    1.72,
+    0.02,
+    0.02,
+    0.05,
+    0.06,
+    0.01,
+    0.03,
+    12.6,
+    101.64,
+    2.94,
+    0.98
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    81.42,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790717811.896799
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K28/speed-32k-3.json

@@ -0,0 +1,487 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K28",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 3,
+ "run_id": "d22ca9d8c7b8",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:36:51",
+ "prompt_tokens": 31602,
+ "completion_tokens": 59,
+ "ttft_s": 10.575,
+ "e2e_s": 11.17,
+ "api_prompt_tps": 2988.5,
+ "api_decode_tps": 97.4,
+ "engine_prompt_tps": 3037.5,
+ "engine_decode_tps": 96.6,
+ "log_lines": [
+  "strata serve: prompt 31602 tokens = 0 reused + 31602 read in 10404 ms (3037.5 tok/s), 59 generated in 611 ms (96.6 tok/s), drafts accepted 41 of 52, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (35040 hits / 35040 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what's there.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 7168,
+   "expert_cache_mib": 13437,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 4557,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717812.0454123,
+    "duration_s": 11.0,
+    "finish": "stop",
+    "prompt_tokens": 31602,
+    "reused": 0,
+    "output_tokens": 59,
+    "engine_generated": 59,
+    "prompt_ms": 10404.1,
+    "decode_ms": 610.6,
+    "decode_tok_s": 96.6,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717800.5571585,
+    "duration_s": 10.8,
+    "finish": "stop",
+    "prompt_tokens": 31631,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 10422.5,
+    "decode_ms": 406.8,
+    "decode_tok_s": 110.6,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717789.1846194,
+    "duration_s": 10.7,
+    "finish": "stop",
+    "prompt_tokens": 28316,
+    "reused": 0,
+    "output_tokens": 57,
+    "engine_generated": 57,
+    "prompt_ms": 10118.2,
+    "decode_ms": 608.0,
+    "decode_tok_s": 93.8,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 3,
+  "totals": {
+   "since": 1790717787.625935,
+   "requests": 3,
+   "prompt_tokens": 91549,
+   "reused": 0,
+   "output_tokens": 161,
+   "prompt_ms": 30944.800000000003,
+   "decode_ms": 1625.4
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 48,
+     "mem_used": 21104623616,
+     "mem_total": 25769803776,
+     "temp": 53,
+     "power": 214.931
+    },
+    {
+     "index": 1,
+     "util": 0,
+     "mem_used": 19548536832,
+     "mem_total": 25769803776,
+     "temp": 53,
+     "power": 199.379
+    }
+   ],
+   "gpu_util": 24.0,
+   "gpu_mem_used": 40653160448,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 53,
+   "gpu_power": 414.31,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 0.666015625,
+   "gpu_pcie_tx_mb": 0.857421875,
+   "cpu": 3.6,
+   "ram_used": 44545851392,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.7062443272525659,
+   "disk_write_mb": 0.11530519628613321,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.5,
+    0.0,
+    0.0,
+    46.5,
+    96.0,
+    72.5,
+    93.0,
+    90.0,
+    95.5,
+    93.5,
+    97.5,
+    41.5,
+    0.0,
+    96.0,
+    93.0,
+    97.5,
+    94.5,
+    97.0,
+    95.0,
+    97.0,
+    93.5,
+    67.0,
+    29.0,
+    50.0,
+    96.5,
+    47.5,
+    95.5,
+    96.5,
+    95.5,
+    62.5,
+    96.5,
+    95.5,
+    50.0,
+    24.0
+   ],
+   "gpu_mem_used": [
+    40447639552,
+    40447639552,
+    40495874048,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40542011392,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448,
+    40653160448
+   ],
+   "gpu_temp": [
+    51,
+    50,
+    50,
+    52,
+    55,
+    54,
+    56,
+    54,
+    56,
+    56,
+    57,
+    54,
+    52,
+    55,
+    54,
+    56,
+    56,
+    56,
+    56,
+    57,
+    57,
+    56,
+    54,
+    53,
+    56,
+    54,
+    57,
+    57,
+    57,
+    56,
+    57,
+    56,
+    57,
+    53
+   ],
+   "gpu_power": [
+    261.46,
+    249.04,
+    248.59,
+    342.07,
+    531.07,
+    533.47,
+    545.68,
+    511.29,
+    533.34,
+    534.58,
+    541.51,
+    420.39,
+    375.37,
+    452.84,
+    528.99,
+    547.53,
+    532.29,
+    524.3,
+    518.92,
+    543.34,
+    532.25,
+    534.03,
+    430.46,
+    354.3,
+    519.1,
+    530.52,
+    534.81,
+    532.5,
+    512.45,
+    532.86,
+    540.0,
+    532.72,
+    513.31,
+    414.31
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.62,
+    182.48,
+    55.88,
+    87.02,
+    80.58,
+    57.5,
+    78.87,
+    83.88,
+    1294.42,
+    46.78,
+    17.17,
+    42.15,
+    1288.27,
+    41.05,
+    75.34,
+    70.76,
+    44.15,
+    79.87,
+    61.61,
+    75.63,
+    42.06,
+    0.62,
+    84.64,
+    74.34,
+    85.5,
+    81.54,
+    0.67,
+    75.72,
+    81.82,
+    82.83,
+    28.8,
+    17.74,
+    0.67
+   ],
+   "cpu": [
+    0.0,
+    6.6,
+    18.0,
+    11.3,
+    10.5,
+    9.8,
+    11.5,
+    13.9,
+    11.4,
+    12.9,
+    7.4,
+    6.1,
+    4.2,
+    6.4,
+    6.0,
+    12.9,
+    11.2,
+    6.1,
+    8.2,
+    8.8,
+    14.0,
+    6.4,
+    4.3,
+    4.2,
+    6.6,
+    6.0,
+    17.8,
+    8.5,
+    6.2,
+    15.1,
+    14.3,
+    6.7,
+    6.9,
+    3.6
+   ],
+   "ram_used": [
+    43799613440,
+    43777974272,
+    43950305280,
+    43962880000,
+    43939622912,
+    43930345472,
+    43932086272,
+    44071780352,
+    44183257088,
+    44182880256,
+    44179062784,
+    44503613440,
+    44015304704,
+    44019281920,
+    44021350400,
+    44034875392,
+    44111585280,
+    44348657664,
+    44344815616,
+    44359872512,
+    44334280704,
+    44327985152,
+    44573519872,
+    44103626752,
+    44105744384,
+    44105732096,
+    44159885312,
+    44275363840,
+    44375539712,
+    44373200896,
+    44318019584,
+    44307988480,
+    44545863680,
+    44545851392
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    129.59,
+    40.83,
+    79.94,
+    84.92,
+    115.02,
+    136.42,
+    117.79,
+    106.04,
+    29.9,
+    1.95,
+    1.72,
+    0.02,
+    0.02,
+    0.05,
+    0.06,
+    0.01,
+    0.03,
+    12.6,
+    101.64,
+    2.94,
+    0.98,
+    0.74,
+    0.02,
+    0.06,
+    0.32,
+    0.08,
+    0.04,
+    0.05,
+    0.04,
+    0.1,
+    0.0,
+    0.71
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    81.42,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790717823.5700235
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K30/speed-32k-1.json

@@ -0,0 +1,608 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K30",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 1,
+ "run_id": "b4895f87f439",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:28:38",
+ "prompt_tokens": 28316,
+ "completion_tokens": 45,
+ "ttft_s": 9.936,
+ "e2e_s": 10.4,
+ "api_prompt_tps": 2849.8,
+ "api_decode_tps": 94.9,
+ "engine_prompt_tps": 2892.0,
+ "engine_decode_tps": 94.1,
+ "log_lines": [
+  "strata serve: prompt 28316 tokens = 0 reused + 28316 read in 9791 ms (2892.0 tok/s), 45 generated in 478 ms (94.1 tok/s), drafts accepted 31 of 37, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (25440 hits / 25440 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what's there.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 7680,
+   "expert_cache_mib": 14575,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 3419,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717318.4067442,
+    "duration_s": 10.3,
+    "finish": "stop",
+    "prompt_tokens": 28316,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 9791.3,
+    "decode_ms": 478.1,
+    "decode_tok_s": 94.1,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717288.2692974,
+    "duration_s": 11.1,
+    "finish": "stop",
+    "prompt_tokens": 28316,
+    "reused": 0,
+    "output_tokens": 56,
+    "engine_generated": 56,
+    "prompt_ms": 10484.4,
+    "decode_ms": 636.0,
+    "decode_tok_s": 88.1,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 2,
+  "totals": {
+   "since": 1790717276.5105639,
+   "requests": 2,
+   "prompt_tokens": 56632,
+   "reused": 0,
+   "output_tokens": 101,
+   "prompt_ms": 20275.699999999997,
+   "decode_ms": 1114.1
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 53,
+     "mem_used": 22306291712,
+     "mem_total": 25769803776,
+     "temp": 51,
+     "power": 200.427
+    },
+    {
+     "index": 1,
+     "util": 46,
+     "mem_used": 18353160192,
+     "mem_total": 25769803776,
+     "temp": 53,
+     "power": 223.879
+    }
+   ],
+   "gpu_util": 49.5,
+   "gpu_mem_used": 40659451904,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 53,
+   "gpu_power": 424.306,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 5.8642578125,
+   "gpu_pcie_tx_mb": 107.4306640625,
+   "cpu": 6.9,
+   "ram_used": 44604223488,
+   "ram_total": 177175990272,
+   "disk_read_mb": 1.1417042620069329,
+   "disk_write_mb": 0.04682067951447989,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    50.0,
+    94.0,
+    63.0,
+    95.0,
+    50.0,
+    92.0,
+    95.0,
+    82.5,
+    97.0,
+    35.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.5,
+    97.5,
+    49.0,
+    94.5,
+    50.0,
+    96.5,
+    53.0,
+    94.5,
+    97.0,
+    49.5
+   ],
+   "gpu_mem_used": [
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40542011392,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40659451904
+   ],
+   "gpu_temp": [
+    49,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    50,
+    52,
+    53,
+    53,
+    53,
+    52,
+    54,
+    51,
+    54,
+    52,
+    50,
+    49,
+    49,
+    49,
+    49,
+    49,
+    49,
+    48,
+    49,
+    48,
+    48,
+    48,
+    49,
+    49,
+    49,
+    49,
+    46,
+    46,
+    53,
+    52,
+    54,
+    52,
+    54,
+    52,
+    54,
+    54,
+    53
+   ],
+   "gpu_power": [
+    257.9,
+    244.84,
+    244.4,
+    244.1,
+    244.29,
+    244.43,
+    244.32,
+    244.0,
+    243.79,
+    243.86,
+    244.04,
+    244.43,
+    304.5,
+    504.99,
+    527.59,
+    513.34,
+    519.55,
+    489.82,
+    537.3,
+    515.01,
+    534.71,
+    416.26,
+    390.46,
+    299.77,
+    260.05,
+    241.54,
+    241.56,
+    241.75,
+    241.63,
+    241.51,
+    241.46,
+    241.4,
+    241.29,
+    241.13,
+    241.31,
+    241.69,
+    241.72,
+    221.92,
+    136.12,
+    67.69,
+    469.97,
+    521.96,
+    512.77,
+    514.47,
+    496.64,
+    522.43,
+    513.55,
+    532.56,
+    424.31
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.67,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.67,
+    1.62,
+    0.67,
+    0.62,
+    0.62,
+    0.62,
+    4319.14,
+    134.51,
+    87.31,
+    96.37,
+    111.91,
+    79.87,
+    41.53,
+    80.25,
+    44.15,
+    15.88,
+    0.67,
+    0.57,
+    0.57,
+    0.57,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.57,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.57,
+    0.81,
+    0.81,
+    44.34,
+    97.08,
+    1308.87,
+    41.25,
+    84.97,
+    155.3,
+    46.68,
+    84.26,
+    3604.32,
+    5.86
+   ],
+   "cpu": [
+    0.0,
+    1.4,
+    4.7,
+    7.8,
+    13.7,
+    1.8,
+    1.4,
+    1.9,
+    1.6,
+    1.4,
+    1.5,
+    9.7,
+    13.3,
+    10.3,
+    10.0,
+    9.4,
+    23.0,
+    17.6,
+    10.6,
+    13.1,
+    6.5,
+    6.2,
+    1.3,
+    8.4,
+    5.4,
+    1.3,
+    1.2,
+    1.8,
+    1.6,
+    0.9,
+    10.0,
+    4.2,
+    0.8,
+    1.8,
+    1.6,
+    2.2,
+    2.6,
+    1.9,
+    2.8,
+    7.4,
+    8.7,
+    7.1,
+    5.6,
+    6.2,
+    14.3,
+    8.5,
+    5.8,
+    9.0,
+    6.9
+   ],
+   "ram_used": [
+    43796508672,
+    43800592384,
+    43805933568,
+    43809234944,
+    43832729600,
+    43832090624,
+    43837464576,
+    43835621376,
+    43830910976,
+    43829395456,
+    43825078272,
+    43852685312,
+    44052480000,
+    44036640768,
+    44033179648,
+    44028084224,
+    44053590016,
+    44291584000,
+    44290129920,
+    44269481984,
+    44257243136,
+    44556734464,
+    44502183936,
+    44524433408,
+    44526993408,
+    44523057152,
+    44523831296,
+    44519899136,
+    44508749824,
+    44508250112,
+    44527558656,
+    44529721344,
+    44527198208,
+    44529672192,
+    44530278400,
+    44537171968,
+    44538560512,
+    44524920832,
+    44552687616,
+    44075163648,
+    44090421248,
+    44086198272,
+    44085055488,
+    44084731904,
+    44364992512,
+    44360019968,
+    44359946240,
+    44359090176,
+    44604223488
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    56.63,
+    73.79,
+    64.08,
+    89.26,
+    71.49,
+    160.33,
+    111.7,
+    115.85,
+    97.53,
+    0.0,
+    3.5,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.56,
+    0.02,
+    0.04,
+    0.03,
+    0.05,
+    0.01,
+    0.03,
+    0.01,
+    0.0,
+    1.14
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790717329.186504
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K30/speed-32k-2.json

@@ -0,0 +1,721 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K30",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 2,
+ "run_id": "f81947893a8b",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:28:49",
+ "prompt_tokens": 31632,
+ "completion_tokens": 48,
+ "ttft_s": 11.011,
+ "e2e_s": 11.496,
+ "api_prompt_tps": 2872.7,
+ "api_decode_tps": 97.0,
+ "engine_prompt_tps": 2926.4,
+ "engine_decode_tps": 96.1,
+ "log_lines": [
+  "strata serve: prompt 31632 tokens = 0 reused + 31632 read in 10809 ms (2926.4 tok/s), 48 generated in 499 ms (96.1 tok/s), drafts accepted 32 of 38, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (27360 hits / 27360 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what's there and identify the last file.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 7680,
+   "expert_cache_mib": 14575,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 3419,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717329.364414,
+    "duration_s": 11.3,
+    "finish": "stop",
+    "prompt_tokens": 31632,
+    "reused": 0,
+    "output_tokens": 48,
+    "engine_generated": 48,
+    "prompt_ms": 10809.3,
+    "decode_ms": 499.4,
+    "decode_tok_s": 96.1,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717318.4067442,
+    "duration_s": 10.3,
+    "finish": "stop",
+    "prompt_tokens": 28316,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 9791.3,
+    "decode_ms": 478.1,
+    "decode_tok_s": 94.1,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717288.2692974,
+    "duration_s": 11.1,
+    "finish": "stop",
+    "prompt_tokens": 28316,
+    "reused": 0,
+    "output_tokens": 56,
+    "engine_generated": 56,
+    "prompt_ms": 10484.4,
+    "decode_ms": 636.0,
+    "decode_tok_s": 88.1,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 3,
+  "totals": {
+   "since": 1790717276.5105639,
+   "requests": 3,
+   "prompt_tokens": 88264,
+   "reused": 0,
+   "output_tokens": 149,
+   "prompt_ms": 31084.999999999996,
+   "decode_ms": 1613.5
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 48,
+     "mem_used": 22306291712,
+     "mem_total": 25769803776,
+     "temp": 51,
+     "power": 211.949
+    },
+    {
+     "index": 1,
+     "util": 41,
+     "mem_used": 18353160192,
+     "mem_total": 25769803776,
+     "temp": 54,
+     "power": 238.158
+    }
+   ],
+   "gpu_util": 44.5,
+   "gpu_mem_used": 40659451904,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 54,
+   "gpu_power": 450.10699999999997,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 16.3544921875,
+   "gpu_pcie_tx_mb": 94.6513671875,
+   "cpu": 12.9,
+   "ram_used": 44387663872,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.417992184024029,
+   "disk_write_mb": 0.0972912842124895,
+   "tok_s": 101.46942145535564,
+   "tok_s_mean": 93.06246895838419
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    50.0,
+    94.0,
+    63.0,
+    95.0,
+    50.0,
+    92.0,
+    95.0,
+    82.5,
+    97.0,
+    35.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.5,
+    97.5,
+    49.0,
+    94.5,
+    50.0,
+    96.5,
+    53.0,
+    94.5,
+    97.0,
+    49.5,
+    50.0,
+    97.5,
+    97.0,
+    98.5,
+    68.5,
+    96.0,
+    49.5,
+    96.0,
+    68.5,
+    97.0,
+    44.5
+   ],
+   "gpu_mem_used": [
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40449736704,
+    40542011392,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904
+   ],
+   "gpu_temp": [
+    49,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    50,
+    52,
+    53,
+    53,
+    53,
+    52,
+    54,
+    51,
+    54,
+    52,
+    50,
+    49,
+    49,
+    49,
+    49,
+    49,
+    49,
+    48,
+    49,
+    48,
+    48,
+    48,
+    49,
+    49,
+    49,
+    49,
+    46,
+    46,
+    53,
+    52,
+    54,
+    52,
+    54,
+    52,
+    54,
+    54,
+    53,
+    50,
+    54,
+    54,
+    55,
+    54,
+    55,
+    52,
+    55,
+    54,
+    55,
+    54
+   ],
+   "gpu_power": [
+    257.9,
+    244.84,
+    244.4,
+    244.1,
+    244.29,
+    244.43,
+    244.32,
+    244.0,
+    243.79,
+    243.86,
+    244.04,
+    244.43,
+    304.5,
+    504.99,
+    527.59,
+    513.34,
+    519.55,
+    489.82,
+    537.3,
+    515.01,
+    534.71,
+    416.26,
+    390.46,
+    299.77,
+    260.05,
+    241.54,
+    241.56,
+    241.75,
+    241.63,
+    241.51,
+    241.46,
+    241.4,
+    241.29,
+    241.13,
+    241.31,
+    241.69,
+    241.72,
+    221.92,
+    136.12,
+    67.69,
+    469.97,
+    521.96,
+    512.77,
+    514.47,
+    496.64,
+    522.43,
+    513.55,
+    532.56,
+    424.31,
+    362.71,
+    481.71,
+    508.96,
+    525.74,
+    511.3,
+    510.79,
+    506.4,
+    523.98,
+    513.03,
+    516.57,
+    450.11
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.67,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.67,
+    1.62,
+    0.67,
+    0.62,
+    0.62,
+    0.62,
+    4319.14,
+    134.51,
+    87.31,
+    96.37,
+    111.91,
+    79.87,
+    41.53,
+    80.25,
+    44.15,
+    15.88,
+    0.67,
+    0.57,
+    0.57,
+    0.57,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.57,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.57,
+    0.81,
+    0.81,
+    44.34,
+    97.08,
+    1308.87,
+    41.25,
+    84.97,
+    155.3,
+    46.68,
+    84.26,
+    3604.32,
+    5.86,
+    45.25,
+    84.11,
+    42.39,
+    128.98,
+    67.52,
+    42.77,
+    92.46,
+    81.82,
+    43.3,
+    95.32,
+    16.35
+   ],
+   "cpu": [
+    0.0,
+    1.4,
+    4.7,
+    7.8,
+    13.7,
+    1.8,
+    1.4,
+    1.9,
+    1.6,
+    1.4,
+    1.5,
+    9.7,
+    13.3,
+    10.3,
+    10.0,
+    9.4,
+    23.0,
+    17.6,
+    10.6,
+    13.1,
+    6.5,
+    6.2,
+    1.3,
+    8.4,
+    5.4,
+    1.3,
+    1.2,
+    1.8,
+    1.6,
+    0.9,
+    10.0,
+    4.2,
+    0.8,
+    1.8,
+    1.6,
+    2.2,
+    2.6,
+    1.9,
+    2.8,
+    7.4,
+    8.7,
+    7.1,
+    5.6,
+    6.2,
+    14.3,
+    8.5,
+    5.8,
+    9.0,
+    6.9,
+    3.9,
+    5.5,
+    5.8,
+    5.9,
+    6.4,
+    7.5,
+    6.6,
+    6.1,
+    8.7,
+    17.4,
+    12.9
+   ],
+   "ram_used": [
+    43796508672,
+    43800592384,
+    43805933568,
+    43809234944,
+    43832729600,
+    43832090624,
+    43837464576,
+    43835621376,
+    43830910976,
+    43829395456,
+    43825078272,
+    43852685312,
+    44052480000,
+    44036640768,
+    44033179648,
+    44028084224,
+    44053590016,
+    44291584000,
+    44290129920,
+    44269481984,
+    44257243136,
+    44556734464,
+    44502183936,
+    44524433408,
+    44526993408,
+    44523057152,
+    44523831296,
+    44519899136,
+    44508749824,
+    44508250112,
+    44527558656,
+    44529721344,
+    44527198208,
+    44529672192,
+    44530278400,
+    44537171968,
+    44538560512,
+    44524920832,
+    44552687616,
+    44075163648,
+    44090421248,
+    44086198272,
+    44085055488,
+    44084731904,
+    44364992512,
+    44360019968,
+    44359946240,
+    44359090176,
+    44604223488,
+    44141965312,
+    44142555136,
+    44129452032,
+    44121694208,
+    44121939968,
+    44354928640,
+    44349378560,
+    44349894656,
+    44349890560,
+    44144226304,
+    44387663872
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    56.63,
+    73.79,
+    64.08,
+    89.26,
+    71.49,
+    160.33,
+    111.7,
+    115.85,
+    97.53,
+    0.0,
+    3.5,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.56,
+    0.02,
+    0.04,
+    0.03,
+    0.05,
+    0.01,
+    0.03,
+    0.01,
+    0.0,
+    1.14,
+    0.4,
+    0.01,
+    0.0,
+    0.03,
+    0.04,
+    0.01,
+    0.03,
+    12.58,
+    71.94,
+    32.9,
+    0.42
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    101.47
+   ]
+  },
+  "time": 1790717341.185252
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-K30/speed-32k-3.json

@@ -0,0 +1,735 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-K30",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 3,
+ "run_id": "cb947708c5cc",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:29:01",
+ "prompt_tokens": 31602,
+ "completion_tokens": 45,
+ "ttft_s": 10.976,
+ "e2e_s": 11.378,
+ "api_prompt_tps": 2879.2,
+ "api_decode_tps": 109.6,
+ "engine_prompt_tps": 2920.6,
+ "engine_decode_tps": 108.0,
+ "log_lines": [
+  "strata serve: prompt 31602 tokens = 0 reused + 31602 read in 10820 ms (2920.6 tok/s), 45 generated in 417 ms (108.0 tok/s), drafts accepted 33 of 37, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (24480 hits / 24480 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what we're working with.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 7680,
+   "expert_cache_mib": 14575,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 3419,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790717341.3189692,
+    "duration_s": 11.2,
+    "finish": "stop",
+    "prompt_tokens": 31602,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 10820.3,
+    "decode_ms": 416.8,
+    "decode_tok_s": 108.0,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717329.364414,
+    "duration_s": 11.3,
+    "finish": "stop",
+    "prompt_tokens": 31632,
+    "reused": 0,
+    "output_tokens": 48,
+    "engine_generated": 48,
+    "prompt_ms": 10809.3,
+    "decode_ms": 499.4,
+    "decode_tok_s": 96.1,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717318.4067442,
+    "duration_s": 10.3,
+    "finish": "stop",
+    "prompt_tokens": 28316,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 9791.3,
+    "decode_ms": 478.1,
+    "decode_tok_s": 94.1,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790717288.2692974,
+    "duration_s": 11.1,
+    "finish": "stop",
+    "prompt_tokens": 28316,
+    "reused": 0,
+    "output_tokens": 56,
+    "engine_generated": 56,
+    "prompt_ms": 10484.4,
+    "decode_ms": 636.0,
+    "decode_tok_s": 88.1,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 4,
+  "totals": {
+   "since": 1790717276.5105639,
+   "requests": 4,
+   "prompt_tokens": 119866,
+   "reused": 0,
+   "output_tokens": 194,
+   "prompt_ms": 41905.299999999996,
+   "decode_ms": 2030.3
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 5,
+     "mem_used": 22306291712,
+     "mem_total": 25769803776,
+     "temp": 49,
+     "power": 227.165
+    },
+    {
+     "index": 1,
+     "util": 42,
+     "mem_used": 18353160192,
+     "mem_total": 25769803776,
+     "temp": 54,
+     "power": 235.691
+    }
+   ],
+   "gpu_util": 23.5,
+   "gpu_mem_used": 40659451904,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 54,
+   "gpu_power": 462.856,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 17.0703125,
+   "gpu_pcie_tx_mb": 56.361328125,
+   "cpu": 5.5,
+   "ram_used": 44383059968,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.38547172180233397,
+   "disk_write_mb": 0.09366602585851105,
+   "tok_s": 121.26075785511577,
+   "tok_s_mean": 112.03069063875886
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.0,
+    50.0,
+    94.0,
+    63.0,
+    95.0,
+    50.0,
+    92.0,
+    95.0,
+    82.5,
+    97.0,
+    35.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.5,
+    97.5,
+    49.0,
+    94.5,
+    50.0,
+    96.5,
+    53.0,
+    94.5,
+    97.0,
+    49.5,
+    50.0,
+    97.5,
+    97.0,
+    98.5,
+    68.5,
+    96.0,
+    49.5,
+    96.0,
+    68.5,
+    97.0,
+    44.5,
+    50.0,
+    85.5,
+    94.5,
+    73.0,
+    79.0,
+    96.0,
+    48.0,
+    95.0,
+    72.5,
+    95.5,
+    23.5
+   ],
+   "gpu_mem_used": [
+    40449736704,
+    40542011392,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40548302848,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40636383232,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904,
+    40659451904
+   ],
+   "gpu_temp": [
+    48,
+    50,
+    52,
+    53,
+    53,
+    53,
+    52,
+    54,
+    51,
+    54,
+    52,
+    50,
+    49,
+    49,
+    49,
+    49,
+    49,
+    49,
+    48,
+    49,
+    48,
+    48,
+    48,
+    49,
+    49,
+    49,
+    49,
+    46,
+    46,
+    53,
+    52,
+    54,
+    52,
+    54,
+    52,
+    54,
+    54,
+    53,
+    50,
+    54,
+    54,
+    55,
+    54,
+    55,
+    52,
+    55,
+    54,
+    55,
+    54,
+    51,
+    53,
+    54,
+    53,
+    54,
+    55,
+    54,
+    55,
+    55,
+    55,
+    54
+   ],
+   "gpu_power": [
+    244.43,
+    304.5,
+    504.99,
+    527.59,
+    513.34,
+    519.55,
+    489.82,
+    537.3,
+    515.01,
+    534.71,
+    416.26,
+    390.46,
+    299.77,
+    260.05,
+    241.54,
+    241.56,
+    241.75,
+    241.63,
+    241.51,
+    241.46,
+    241.4,
+    241.29,
+    241.13,
+    241.31,
+    241.69,
+    241.72,
+    221.92,
+    136.12,
+    67.69,
+    469.97,
+    521.96,
+    512.77,
+    514.47,
+    496.64,
+    522.43,
+    513.55,
+    532.56,
+    424.31,
+    362.71,
+    481.71,
+    508.96,
+    525.74,
+    511.3,
+    510.79,
+    506.4,
+    523.98,
+    513.03,
+    516.57,
+    450.11,
+    369.53,
+    481.25,
+    509.29,
+    527.58,
+    511.62,
+    510.74,
+    510.07,
+    527.16,
+    513.42,
+    533.96,
+    462.86
+   ],
+   "gpu_pcie_rx_mb": [
+    0.62,
+    4319.14,
+    134.51,
+    87.31,
+    96.37,
+    111.91,
+    79.87,
+    41.53,
+    80.25,
+    44.15,
+    15.88,
+    0.67,
+    0.57,
+    0.57,
+    0.57,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.57,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.57,
+    0.81,
+    0.81,
+    44.34,
+    97.08,
+    1308.87,
+    41.25,
+    84.97,
+    155.3,
+    46.68,
+    84.26,
+    3604.32,
+    5.86,
+    45.25,
+    84.11,
+    42.39,
+    128.98,
+    67.52,
+    42.77,
+    92.46,
+    81.82,
+    43.3,
+    95.32,
+    16.35,
+    43.1,
+    79.92,
+    41.63,
+    65.23,
+    80.39,
+    37.1,
+    81.92,
+    1273.96,
+    41.01,
+    79.15,
+    17.07
+   ],
+   "cpu": [
+    9.7,
+    13.3,
+    10.3,
+    10.0,
+    9.4,
+    23.0,
+    17.6,
+    10.6,
+    13.1,
+    6.5,
+    6.2,
+    1.3,
+    8.4,
+    5.4,
+    1.3,
+    1.2,
+    1.8,
+    1.6,
+    0.9,
+    10.0,
+    4.2,
+    0.8,
+    1.8,
+    1.6,
+    2.2,
+    2.6,
+    1.9,
+    2.8,
+    7.4,
+    8.7,
+    7.1,
+    5.6,
+    6.2,
+    14.3,
+    8.5,
+    5.8,
+    9.0,
+    6.9,
+    3.9,
+    5.5,
+    5.8,
+    5.9,
+    6.4,
+    7.5,
+    6.6,
+    6.1,
+    8.7,
+    17.4,
+    12.9,
+    4.0,
+    6.3,
+    7.4,
+    6.1,
+    5.4,
+    6.6,
+    5.7,
+    6.7,
+    9.3,
+    6.7,
+    5.5
+   ],
+   "ram_used": [
+    43852685312,
+    44052480000,
+    44036640768,
+    44033179648,
+    44028084224,
+    44053590016,
+    44291584000,
+    44290129920,
+    44269481984,
+    44257243136,
+    44556734464,
+    44502183936,
+    44524433408,
+    44526993408,
+    44523057152,
+    44523831296,
+    44519899136,
+    44508749824,
+    44508250112,
+    44527558656,
+    44529721344,
+    44527198208,
+    44529672192,
+    44530278400,
+    44537171968,
+    44538560512,
+    44524920832,
+    44552687616,
+    44075163648,
+    44090421248,
+    44086198272,
+    44085055488,
+    44084731904,
+    44364992512,
+    44360019968,
+    44359946240,
+    44359090176,
+    44604223488,
+    44141965312,
+    44142555136,
+    44129452032,
+    44121694208,
+    44121939968,
+    44354928640,
+    44349378560,
+    44349894656,
+    44349890560,
+    44144226304,
+    44387663872,
+    44206063616,
+    44194983936,
+    44169220096,
+    44150177792,
+    44142342144,
+    44137152512,
+    44138057728,
+    44126892032,
+    44160794624,
+    44161884160,
+    44383059968
+   ],
+   "disk_read_mb": [
+    56.63,
+    73.79,
+    64.08,
+    89.26,
+    71.49,
+    160.33,
+    111.7,
+    115.85,
+    97.53,
+    0.0,
+    3.5,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.56,
+    0.02,
+    0.04,
+    0.03,
+    0.05,
+    0.01,
+    0.03,
+    0.01,
+    0.0,
+    1.14,
+    0.4,
+    0.01,
+    0.0,
+    0.03,
+    0.04,
+    0.01,
+    0.03,
+    12.58,
+    71.94,
+    32.9,
+    0.42,
+    0.53,
+    0.06,
+    0.03,
+    0.08,
+    0.09,
+    0.04,
+    0.08,
+    0.03,
+    0.02,
+    0.22,
+    0.39
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    101.47,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    121.26
+   ]
+  },
+  "time": 1790717353.0661266
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-auto/speed-32k-1.json

@@ -0,0 +1,585 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-auto",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 1,
+ "run_id": "3e44ccd7ec28",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:18:00",
+ "prompt_tokens": 28314,
+ "completion_tokens": 48,
+ "ttft_s": 11.385,
+ "e2e_s": 11.891,
+ "api_prompt_tps": 2486.9,
+ "api_decode_tps": 93.0,
+ "engine_prompt_tps": 2524.7,
+ "engine_decode_tps": 88.5,
+ "log_lines": [
+  "strata serve: prompt 28314 tokens = 0 reused + 28314 read in 11215 ms (2524.7 tok/s), 48 generated in 542 ms (88.5 tok/s), drafts accepted 34 of 36, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (24958 hits / 24960 lookups)"
+ ],
+ "answer_head": "I'll first look at the repository structure to understand what files exist and identify the last file.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 4864,
+   "expert_cache_mib": 8968,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 9025,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790716680.7795944,
+    "duration_s": 11.8,
+    "finish": "stop",
+    "prompt_tokens": 28314,
+    "reused": 0,
+    "output_tokens": 48,
+    "engine_generated": 48,
+    "prompt_ms": 11214.6,
+    "decode_ms": 542.2,
+    "decode_tok_s": 88.5,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 1,
+  "totals": {
+   "since": 1790716641.243247,
+   "requests": 1,
+   "prompt_tokens": 28314,
+   "reused": 0,
+   "output_tokens": 48,
+   "prompt_ms": 11214.6,
+   "decode_ms": 542.2
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 2,
+     "mem_used": 16383934464,
+     "mem_total": 25769803776,
+     "temp": 43,
+     "power": 147.336
+    },
+    {
+     "index": 1,
+     "util": 7,
+     "mem_used": 24227282944,
+     "mem_total": 25769803776,
+     "temp": 48,
+     "power": 266.007
+    }
+   ],
+   "gpu_util": 4.5,
+   "gpu_mem_used": 40611217408,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 48,
+   "gpu_power": 413.343,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 16.8310546875,
+   "gpu_pcie_tx_mb": 71.810546875,
+   "cpu": 8.4,
+   "ram_used": 44637356032,
+   "ram_total": 177175990272,
+   "disk_read_mb": 2.277384309569965,
+   "disk_write_mb": 0.07927603609262536,
+   "tok_s": 96.0473472439008,
+   "tok_s_mean": 90.3424282028167
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.5,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    2.0,
+    48.0,
+    91.5,
+    69.0,
+    77.0,
+    91.0,
+    93.0,
+    49.5,
+    94.0,
+    50.0,
+    4.5
+   ],
+   "gpu_mem_used": [
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40489582592,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40611217408
+   ],
+   "gpu_temp": [
+    44,
+    43,
+    43,
+    43,
+    43,
+    43,
+    44,
+    44,
+    43,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    41,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    43,
+    49,
+    50,
+    50,
+    50,
+    50,
+    50,
+    50,
+    51,
+    51,
+    48
+   ],
+   "gpu_power": [
+    253.73,
+    239.29,
+    238.99,
+    238.62,
+    238.58,
+    238.53,
+    238.39,
+    238.34,
+    238.4,
+    238.51,
+    238.61,
+    238.53,
+    238.49,
+    238.83,
+    238.96,
+    238.97,
+    226.8,
+    148.88,
+    73.97,
+    64.38,
+    63.94,
+    63.69,
+    63.56,
+    63.75,
+    63.53,
+    63.8,
+    63.68,
+    63.62,
+    63.84,
+    63.74,
+    63.81,
+    64.11,
+    63.92,
+    63.72,
+    63.85,
+    63.64,
+    63.78,
+    139.81,
+    418.68,
+    508.54,
+    520.36,
+    495.57,
+    522.4,
+    506.1,
+    501.02,
+    508.77,
+    509.32,
+    413.34
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.67,
+    0.71,
+    0.57,
+    0.62,
+    0.57,
+    0.67,
+    0.57,
+    0.67,
+    0.62,
+    0.57,
+    0.67,
+    0.62,
+    0.57,
+    1.05,
+    0.57,
+    0.76,
+    0.81,
+    0.81,
+    0.81,
+    0.76,
+    0.76,
+    0.81,
+    0.86,
+    1.43,
+    0.81,
+    0.81,
+    0.76,
+    0.86,
+    0.81,
+    0.76,
+    0.95,
+    0.86,
+    0.86,
+    0.76,
+    0.86,
+    0.86,
+    70.24,
+    68.14,
+    64.66,
+    75.24,
+    42.29,
+    84.73,
+    70.48,
+    75.05,
+    54.45,
+    44.44,
+    16.83
+   ],
+   "cpu": [
+    0.0,
+    0.6,
+    1.0,
+    1.6,
+    2.5,
+    1.0,
+    3.1,
+    8.1,
+    6.5,
+    1.2,
+    1.9,
+    2.1,
+    1.5,
+    3.2,
+    2.4,
+    1.3,
+    2.0,
+    1.4,
+    1.3,
+    0.9,
+    0.9,
+    14.0,
+    6.6,
+    2.5,
+    2.7,
+    1.7,
+    1.2,
+    0.6,
+    1.1,
+    1.2,
+    1.7,
+    1.3,
+    1.4,
+    2.7,
+    4.4,
+    12.3,
+    12.4,
+    11.4,
+    12.5,
+    10.3,
+    9.0,
+    12.2,
+    12.1,
+    12.5,
+    11.3,
+    10.4,
+    5.8,
+    8.4
+   ],
+   "ram_used": [
+    43649658880,
+    43652177920,
+    43664764928,
+    43666993152,
+    43672375296,
+    43665145856,
+    43695276032,
+    43759751168,
+    43760455680,
+    43757346816,
+    43754053632,
+    43711803392,
+    43717255168,
+    43692584960,
+    43693260800,
+    43687956480,
+    43682111488,
+    43635728384,
+    43632320512,
+    43636883456,
+    43633815552,
+    43735252992,
+    43881848832,
+    43881005056,
+    43875524608,
+    43879301120,
+    43878330368,
+    43866976256,
+    43862958080,
+    43863728128,
+    43854176256,
+    43855548416,
+    43854200832,
+    43859615744,
+    43895934976,
+    43929411584,
+    43962118144,
+    44169498624,
+    44107767808,
+    44110077952,
+    44109590528,
+    44111515648,
+    44233150464,
+    44346421248,
+    44340047872,
+    44335108096,
+    44329865216,
+    44637356032
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    129.56,
+    55.21,
+    65.53,
+    55.86,
+    128.68,
+    113.77,
+    117.74,
+    106.28,
+    68.13,
+    0.0,
+    2.28
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    96.05
+   ]
+  },
+  "time": 1790716693.048385
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-auto/speed-32k-2.json

@@ -0,0 +1,707 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-auto",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 2,
+ "run_id": "0b6b57dfa6a4",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:18:13",
+ "prompt_tokens": 31634,
+ "completion_tokens": 55,
+ "ttft_s": 11.855,
+ "e2e_s": 12.398,
+ "api_prompt_tps": 2668.4,
+ "api_decode_tps": 99.4,
+ "engine_prompt_tps": 2704.3,
+ "engine_decode_tps": 98.6,
+ "log_lines": [
+  "strata serve: prompt 31634 tokens = 0 reused + 31634 read in 11698 ms (2704.3 tok/s), 55 generated in 558 ms (98.6 tok/s), drafts accepted 38 of 44, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (29759 hits / 29760 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what we're working with.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 4864,
+   "expert_cache_mib": 8968,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 9025,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790716693.1835682,
+    "duration_s": 12.3,
+    "finish": "stop",
+    "prompt_tokens": 31634,
+    "reused": 0,
+    "output_tokens": 55,
+    "engine_generated": 55,
+    "prompt_ms": 11697.7,
+    "decode_ms": 557.8,
+    "decode_tok_s": 98.6,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790716680.7795944,
+    "duration_s": 11.8,
+    "finish": "stop",
+    "prompt_tokens": 28314,
+    "reused": 0,
+    "output_tokens": 48,
+    "engine_generated": 48,
+    "prompt_ms": 11214.6,
+    "decode_ms": 542.2,
+    "decode_tok_s": 88.5,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 2,
+  "totals": {
+   "since": 1790716641.243247,
+   "requests": 2,
+   "prompt_tokens": 59948,
+   "reused": 0,
+   "output_tokens": 103,
+   "prompt_ms": 22912.300000000003,
+   "decode_ms": 1100.0
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 30,
+     "mem_used": 16392323072,
+     "mem_total": 25769803776,
+     "temp": 45,
+     "power": 154.497
+    },
+    {
+     "index": 1,
+     "util": 0,
+     "mem_used": 24241963008,
+     "mem_total": 25769803776,
+     "temp": 47,
+     "power": 250.412
+    }
+   ],
+   "gpu_util": 15.0,
+   "gpu_mem_used": 40634286080,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 47,
+   "gpu_power": 404.909,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 19.310546875,
+   "gpu_pcie_tx_mb": 48.8271484375,
+   "cpu": 8.6,
+   "ram_used": 44481728512,
+   "ram_total": 177175990272,
+   "disk_read_mb": 1.583864660002197,
+   "disk_write_mb": 0.12238954190926069,
+   "tok_s": 112.53532236859756,
+   "tok_s_mean": 97.92814776699883
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.5,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    2.0,
+    48.0,
+    91.5,
+    69.0,
+    77.0,
+    91.0,
+    93.0,
+    49.5,
+    94.0,
+    50.0,
+    4.5,
+    0.5,
+    94.5,
+    73.5,
+    72.5,
+    96.5,
+    49.0,
+    97.5,
+    97.5,
+    48.5,
+    94.0,
+    48.5,
+    15.0
+   ],
+   "gpu_mem_used": [
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40489582592,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40634286080
+   ],
+   "gpu_temp": [
+    44,
+    43,
+    43,
+    43,
+    43,
+    43,
+    44,
+    44,
+    43,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    41,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    43,
+    49,
+    50,
+    50,
+    50,
+    50,
+    50,
+    50,
+    51,
+    51,
+    48,
+    45,
+    51,
+    51,
+    50,
+    51,
+    51,
+    51,
+    51,
+    51,
+    51,
+    51,
+    47
+   ],
+   "gpu_power": [
+    253.73,
+    239.29,
+    238.99,
+    238.62,
+    238.58,
+    238.53,
+    238.39,
+    238.34,
+    238.4,
+    238.51,
+    238.61,
+    238.53,
+    238.49,
+    238.83,
+    238.96,
+    238.97,
+    226.8,
+    148.88,
+    73.97,
+    64.38,
+    63.94,
+    63.69,
+    63.56,
+    63.75,
+    63.53,
+    63.8,
+    63.68,
+    63.62,
+    63.84,
+    63.74,
+    63.81,
+    64.11,
+    63.92,
+    63.72,
+    63.85,
+    63.64,
+    63.78,
+    139.81,
+    418.68,
+    508.54,
+    520.36,
+    495.57,
+    522.4,
+    506.1,
+    501.02,
+    508.77,
+    509.32,
+    413.34,
+    344.59,
+    491.91,
+    520.34,
+    491.14,
+    524.22,
+    495.09,
+    489.28,
+    512.02,
+    509.99,
+    497.54,
+    503.94,
+    404.91
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    0.67,
+    0.71,
+    0.57,
+    0.62,
+    0.57,
+    0.67,
+    0.57,
+    0.67,
+    0.62,
+    0.57,
+    0.67,
+    0.62,
+    0.57,
+    1.05,
+    0.57,
+    0.76,
+    0.81,
+    0.81,
+    0.81,
+    0.76,
+    0.76,
+    0.81,
+    0.86,
+    1.43,
+    0.81,
+    0.81,
+    0.76,
+    0.86,
+    0.81,
+    0.76,
+    0.95,
+    0.86,
+    0.86,
+    0.76,
+    0.86,
+    0.86,
+    70.24,
+    68.14,
+    64.66,
+    75.24,
+    42.29,
+    84.73,
+    70.48,
+    75.05,
+    54.45,
+    44.44,
+    16.83,
+    43.1,
+    73.43,
+    85.92,
+    85.16,
+    1285.6,
+    83.21,
+    5496.41,
+    73.67,
+    83.68,
+    89.36,
+    52.83,
+    19.31
+   ],
+   "cpu": [
+    0.0,
+    0.6,
+    1.0,
+    1.6,
+    2.5,
+    1.0,
+    3.1,
+    8.1,
+    6.5,
+    1.2,
+    1.9,
+    2.1,
+    1.5,
+    3.2,
+    2.4,
+    1.3,
+    2.0,
+    1.4,
+    1.3,
+    0.9,
+    0.9,
+    14.0,
+    6.6,
+    2.5,
+    2.7,
+    1.7,
+    1.2,
+    0.6,
+    1.1,
+    1.2,
+    1.7,
+    1.3,
+    1.4,
+    2.7,
+    4.4,
+    12.3,
+    12.4,
+    11.4,
+    12.5,
+    10.3,
+    9.0,
+    12.2,
+    12.1,
+    12.5,
+    11.3,
+    10.4,
+    5.8,
+    8.4,
+    5.5,
+    16.9,
+    8.9,
+    8.2,
+    6.7,
+    6.4,
+    6.4,
+    5.5,
+    7.3,
+    10.1,
+    6.1,
+    8.6
+   ],
+   "ram_used": [
+    43649658880,
+    43652177920,
+    43664764928,
+    43666993152,
+    43672375296,
+    43665145856,
+    43695276032,
+    43759751168,
+    43760455680,
+    43757346816,
+    43754053632,
+    43711803392,
+    43717255168,
+    43692584960,
+    43693260800,
+    43687956480,
+    43682111488,
+    43635728384,
+    43632320512,
+    43636883456,
+    43633815552,
+    43735252992,
+    43881848832,
+    43881005056,
+    43875524608,
+    43879301120,
+    43878330368,
+    43866976256,
+    43862958080,
+    43863728128,
+    43854176256,
+    43855548416,
+    43854200832,
+    43859615744,
+    43895934976,
+    43929411584,
+    43962118144,
+    44169498624,
+    44107767808,
+    44110077952,
+    44109590528,
+    44111515648,
+    44233150464,
+    44346421248,
+    44340047872,
+    44335108096,
+    44329865216,
+    44637356032,
+    44551315456,
+    44588969984,
+    44562165760,
+    44546224128,
+    44540850176,
+    44543295488,
+    44547391488,
+    44375429120,
+    44370026496,
+    44363567104,
+    44368113664,
+    44481728512
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    129.56,
+    55.21,
+    65.53,
+    55.86,
+    128.68,
+    113.77,
+    117.74,
+    106.28,
+    68.13,
+    0.0,
+    2.28,
+    1.11,
+    0.12,
+    0.02,
+    0.05,
+    0.05,
+    0.01,
+    0.03,
+    0.0,
+    25.35,
+    92.15,
+    0.01,
+    1.58
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    96.05,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    112.54
+   ]
+  },
+  "time": 1790716705.9498026
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-Coder-2x3090-auto/speed-32k-3.json

@@ -0,0 +1,721 @@
+{
+ "label": "native-v0.1.26-Coder-2x3090-auto",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 3,
+ "run_id": "caa0b992dd74",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:18:25",
+ "prompt_tokens": 31601,
+ "completion_tokens": 45,
+ "ttft_s": 11.847,
+ "e2e_s": 12.249,
+ "api_prompt_tps": 2667.3,
+ "api_decode_tps": 109.5,
+ "engine_prompt_tps": 2704.5,
+ "engine_decode_tps": 108.1,
+ "log_lines": [
+  "strata serve: prompt 31601 tokens = 0 reused + 31601 read in 11684 ms (2704.5 tok/s), 45 generated in 416 ms (108.1 tok/s), drafts accepted 33 of 36, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 100.0% (24000 hits / 24000 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what we're working with.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-coder-iq1_m",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 4864,
+   "expert_cache_mib": 8968,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 9025,
+   "cvec": 0,
+   "arena_mib": 23981,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790716706.0904436,
+    "duration_s": 12.1,
+    "finish": "stop",
+    "prompt_tokens": 31601,
+    "reused": 0,
+    "output_tokens": 45,
+    "engine_generated": 45,
+    "prompt_ms": 11684.5,
+    "decode_ms": 416.2,
+    "decode_tok_s": 108.1,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790716693.1835682,
+    "duration_s": 12.3,
+    "finish": "stop",
+    "prompt_tokens": 31634,
+    "reused": 0,
+    "output_tokens": 55,
+    "engine_generated": 55,
+    "prompt_ms": 11697.7,
+    "decode_ms": 557.8,
+    "decode_tok_s": 98.6,
+    "hit_rate": 1.0
+   },
+   {
+    "projection": null,
+    "time": 1790716680.7795944,
+    "duration_s": 11.8,
+    "finish": "stop",
+    "prompt_tokens": 28314,
+    "reused": 0,
+    "output_tokens": 48,
+    "engine_generated": 48,
+    "prompt_ms": 11214.6,
+    "decode_ms": 542.2,
+    "decode_tok_s": 88.5,
+    "hit_rate": 1.0
+   }
+  ],
+  "requests_kept": 3,
+  "totals": {
+   "since": 1790716641.243247,
+   "requests": 3,
+   "prompt_tokens": 91549,
+   "reused": 0,
+   "output_tokens": 148,
+   "prompt_ms": 34596.8,
+   "decode_ms": 1516.2
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 30,
+     "mem_used": 16392323072,
+     "mem_total": 25769803776,
+     "temp": 46,
+     "power": 161.526
+    },
+    {
+     "index": 1,
+     "util": 0,
+     "mem_used": 24241963008,
+     "mem_total": 25769803776,
+     "temp": 48,
+     "power": 223.689
+    }
+   ],
+   "gpu_util": 15.0,
+   "gpu_mem_used": 40634286080,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 48,
+   "gpu_power": 385.21500000000003,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 0.5703125,
+   "gpu_pcie_tx_mb": 0.857421875,
+   "cpu": 6.1,
+   "ram_used": 44274470912,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.14419269932051038,
+   "disk_write_mb": 0.2595468587769187,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    2.0,
+    48.0,
+    91.5,
+    69.0,
+    77.0,
+    91.0,
+    93.0,
+    49.5,
+    94.0,
+    50.0,
+    4.5,
+    0.5,
+    94.5,
+    73.5,
+    72.5,
+    96.5,
+    49.0,
+    97.5,
+    97.5,
+    48.5,
+    94.0,
+    48.5,
+    15.0,
+    0.0,
+    97.5,
+    49.0,
+    93.5,
+    72.5,
+    70.5,
+    97.0,
+    95.5,
+    50.0,
+    96.0,
+    50.0,
+    15.0
+   ],
+   "gpu_mem_used": [
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40426668032,
+    40489582592,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40521039872,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40611217408,
+    40634286080,
+    40634286080,
+    40634286080,
+    40634286080,
+    40634286080,
+    40634286080,
+    40634286080,
+    40634286080,
+    40634286080,
+    40634286080,
+    40634286080,
+    40634286080,
+    40634286080
+   ],
+   "gpu_temp": [
+    44,
+    44,
+    44,
+    44,
+    44,
+    41,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    40,
+    43,
+    49,
+    50,
+    50,
+    50,
+    50,
+    50,
+    50,
+    51,
+    51,
+    48,
+    45,
+    51,
+    51,
+    50,
+    51,
+    51,
+    51,
+    51,
+    51,
+    51,
+    51,
+    47,
+    45,
+    51,
+    51,
+    51,
+    51,
+    51,
+    51,
+    51,
+    51,
+    52,
+    52,
+    48
+   ],
+   "gpu_power": [
+    238.49,
+    238.83,
+    238.96,
+    238.97,
+    226.8,
+    148.88,
+    73.97,
+    64.38,
+    63.94,
+    63.69,
+    63.56,
+    63.75,
+    63.53,
+    63.8,
+    63.68,
+    63.62,
+    63.84,
+    63.74,
+    63.81,
+    64.11,
+    63.92,
+    63.72,
+    63.85,
+    63.64,
+    63.78,
+    139.81,
+    418.68,
+    508.54,
+    520.36,
+    495.57,
+    522.4,
+    506.1,
+    501.02,
+    508.77,
+    509.32,
+    413.34,
+    344.59,
+    491.91,
+    520.34,
+    491.14,
+    524.22,
+    495.09,
+    489.28,
+    512.02,
+    509.99,
+    497.54,
+    503.94,
+    404.91,
+    336.42,
+    502.95,
+    510.85,
+    498.42,
+    519.36,
+    492.86,
+    501.0,
+    522.94,
+    497.46,
+    508.62,
+    494.37,
+    385.22
+   ],
+   "gpu_pcie_rx_mb": [
+    0.62,
+    0.57,
+    1.05,
+    0.57,
+    0.76,
+    0.81,
+    0.81,
+    0.81,
+    0.76,
+    0.76,
+    0.81,
+    0.86,
+    1.43,
+    0.81,
+    0.81,
+    0.76,
+    0.86,
+    0.81,
+    0.76,
+    0.95,
+    0.86,
+    0.86,
+    0.76,
+    0.86,
+    0.86,
+    70.24,
+    68.14,
+    64.66,
+    75.24,
+    42.29,
+    84.73,
+    70.48,
+    75.05,
+    54.45,
+    44.44,
+    16.83,
+    43.1,
+    73.43,
+    85.92,
+    85.16,
+    1285.6,
+    83.21,
+    5496.41,
+    73.67,
+    83.68,
+    89.36,
+    52.83,
+    19.31,
+    45.11,
+    82.73,
+    85.31,
+    43.06,
+    94.36,
+    41.63,
+    73.48,
+    42.01,
+    87.26,
+    45.92,
+    121.97,
+    0.57
+   ],
+   "cpu": [
+    1.5,
+    3.2,
+    2.4,
+    1.3,
+    2.0,
+    1.4,
+    1.3,
+    0.9,
+    0.9,
+    14.0,
+    6.6,
+    2.5,
+    2.7,
+    1.7,
+    1.2,
+    0.6,
+    1.1,
+    1.2,
+    1.7,
+    1.3,
+    1.4,
+    2.7,
+    4.4,
+    12.3,
+    12.4,
+    11.4,
+    12.5,
+    10.3,
+    9.0,
+    12.2,
+    12.1,
+    12.5,
+    11.3,
+    10.4,
+    5.8,
+    8.4,
+    5.5,
+    16.9,
+    8.9,
+    8.2,
+    6.7,
+    6.4,
+    6.4,
+    5.5,
+    7.3,
+    10.1,
+    6.1,
+    8.6,
+    3.1,
+    6.2,
+    9.6,
+    17.9,
+    6.1,
+    7.4,
+    6.0,
+    6.4,
+    6.4,
+    5.7,
+    5.9,
+    6.1
+   ],
+   "ram_used": [
+    43717255168,
+    43692584960,
+    43693260800,
+    43687956480,
+    43682111488,
+    43635728384,
+    43632320512,
+    43636883456,
+    43633815552,
+    43735252992,
+    43881848832,
+    43881005056,
+    43875524608,
+    43879301120,
+    43878330368,
+    43866976256,
+    43862958080,
+    43863728128,
+    43854176256,
+    43855548416,
+    43854200832,
+    43859615744,
+    43895934976,
+    43929411584,
+    43962118144,
+    44169498624,
+    44107767808,
+    44110077952,
+    44109590528,
+    44111515648,
+    44233150464,
+    44346421248,
+    44340047872,
+    44335108096,
+    44329865216,
+    44637356032,
+    44551315456,
+    44588969984,
+    44562165760,
+    44546224128,
+    44540850176,
+    44543295488,
+    44547391488,
+    44375429120,
+    44370026496,
+    44363567104,
+    44368113664,
+    44481728512,
+    44224720896,
+    44216463360,
+    44188299264,
+    44025966592,
+    44017278976,
+    44014284800,
+    44060004352,
+    44042358784,
+    44044165120,
+    44044423168,
+    44044165120,
+    44274470912
+   ],
+   "disk_read_mb": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    129.56,
+    55.21,
+    65.53,
+    55.86,
+    128.68,
+    113.77,
+    117.74,
+    106.28,
+    68.13,
+    0.0,
+    2.28,
+    1.11,
+    0.12,
+    0.02,
+    0.05,
+    0.05,
+    0.01,
+    0.03,
+    0.0,
+    25.35,
+    92.15,
+    0.01,
+    1.58,
+    0.57,
+    0.06,
+    0.06,
+    0.05,
+    0.08,
+    0.04,
+    0.07,
+    0.01,
+    0.04,
+    0.15,
+    0.0,
+    0.14
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    96.05,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    112.54,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790716718.7022452
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-IQ3_S-2x3090-auto-needle/needle-16k-1.json

@@ -0,0 +1,750 @@
+{
+ "label": "native-v0.1.26-IQ3_S-2x3090-auto-needle",
+ "mode": "needle",
+ "ctx": "16k",
+ "target_tokens": 16384,
+ "run": 1,
+ "run_id": "1e52cb484c7f",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:55:17",
+ "prompt_tokens": 17345,
+ "completion_tokens": 8,
+ "ttft_s": 23.389,
+ "e2e_s": 23.454,
+ "api_prompt_tps": 741.6,
+ "api_decode_tps": 106.6,
+ "engine_prompt_tps": 744.7,
+ "engine_decode_tps": 101.7,
+ "log_lines": [
+  "strata serve: prompt 17345 tokens = 0 reused + 17345 read in 23292 ms (744.7 tok/s), 8 generated in 79 ms (101.7 tok/s), drafts accepted 6 of 6, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 96.3% (4159 hits / 4317 lookups)"
+ ],
+ "answer_head": "A466BDE8",
+ "needle_found": true,
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-iq3_s",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 9376,
+   "expert_cache_mib": 17297,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 635,
+   "cvec": 0,
+   "arena_mib": 47962,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790718917.8830457,
+    "duration_s": 23.4,
+    "finish": "stop",
+    "prompt_tokens": 17345,
+    "reused": 0,
+    "output_tokens": 8,
+    "engine_generated": 8,
+    "prompt_ms": 23292.2,
+    "decode_ms": 78.7,
+    "decode_tok_s": 101.7,
+    "hit_rate": 0.963
+   },
+   {
+    "projection": null,
+    "time": 1790718906.5660036,
+    "duration_s": 10.7,
+    "finish": "stop",
+    "prompt_tokens": 7491,
+    "reused": 0,
+    "output_tokens": 8,
+    "engine_generated": 8,
+    "prompt_ms": 10625.3,
+    "decode_ms": 109.4,
+    "decode_tok_s": 73.1,
+    "hit_rate": 0.902
+   },
+   {
+    "projection": null,
+    "time": 1790718828.4807332,
+    "duration_s": 42.6,
+    "finish": "stop",
+    "prompt_tokens": 31604,
+    "reused": 0,
+    "output_tokens": 49,
+    "engine_generated": 49,
+    "prompt_ms": 42110.8,
+    "decode_ms": 460.9,
+    "decode_tok_s": 106.3,
+    "hit_rate": 0.991
+   },
+   {
+    "projection": null,
+    "time": 1790718784.8375118,
+    "duration_s": 43.0,
+    "finish": "stop",
+    "prompt_tokens": 31633,
+    "reused": 0,
+    "output_tokens": 88,
+    "engine_generated": 88,
+    "prompt_ms": 42216.7,
+    "decode_ms": 776.7,
+    "decode_tok_s": 113.3,
+    "hit_rate": 0.978
+   },
+   {
+    "projection": null,
+    "time": 1790718743.8685048,
+    "duration_s": 40.3,
+    "finish": "stop",
+    "prompt_tokens": 28315,
+    "reused": 0,
+    "output_tokens": 84,
+    "engine_generated": 84,
+    "prompt_ms": 39286.5,
+    "decode_ms": 1011.1,
+    "decode_tok_s": 83.1,
+    "hit_rate": 0.949
+   }
+  ],
+  "requests_kept": 5,
+  "totals": {
+   "since": 1790718725.4039552,
+   "requests": 5,
+   "prompt_tokens": 116388,
+   "reused": 0,
+   "output_tokens": 237,
+   "prompt_ms": 157531.5,
+   "decode_ms": 2436.8
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 5,
+     "mem_used": 25212944384,
+     "mem_total": 25769803776,
+     "temp": 46,
+     "power": 125.093
+    },
+    {
+     "index": 1,
+     "util": 0,
+     "mem_used": 24227282944,
+     "mem_total": 25769803776,
+     "temp": 51,
+     "power": 215.964
+    }
+   ],
+   "gpu_util": 2.5,
+   "gpu_mem_used": 49440227328,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 51,
+   "gpu_power": 341.057,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 0.666015625,
+   "gpu_pcie_tx_mb": 0.9052734375,
+   "cpu": 16.5,
+   "ram_used": 70477971456,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.17303348536954039,
+   "disk_write_mb": 0.0036048642785320916,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    37.0,
+    28.0,
+    22.5,
+    30.0,
+    37.0,
+    18.0,
+    29.0,
+    22.0,
+    21.0,
+    0.5,
+    50.0,
+    34.5,
+    25.0,
+    60.5,
+    31.5,
+    26.0,
+    33.5,
+    46.5,
+    25.0,
+    31.5,
+    21.0,
+    30.0,
+    35.0,
+    37.0,
+    32.5,
+    22.0,
+    26.5,
+    19.5,
+    49.5,
+    26.5,
+    21.0,
+    2.5
+   ],
+   "gpu_mem_used": [
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328
+   ],
+   "gpu_temp": [
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    45,
+    45,
+    45,
+    45,
+    45,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    50,
+    49,
+    51,
+    51,
+    51,
+    51,
+    50,
+    51,
+    52,
+    50,
+    49,
+    49,
+    51,
+    52,
+    50,
+    52,
+    51,
+    51,
+    51,
+    51,
+    52,
+    51,
+    52,
+    51,
+    51,
+    52,
+    52,
+    51,
+    52,
+    52,
+    53,
+    51
+   ],
+   "gpu_power": [
+    242.53,
+    242.44,
+    242.38,
+    242.52,
+    242.49,
+    242.46,
+    242.59,
+    242.37,
+    242.36,
+    242.5,
+    242.54,
+    140.5,
+    84.6,
+    65.59,
+    65.03,
+    64.81,
+    64.81,
+    64.9,
+    64.51,
+    64.65,
+    64.87,
+    64.67,
+    64.8,
+    64.5,
+    64.56,
+    64.64,
+    64.52,
+    64.48,
+    252.37,
+    388.02,
+    363.78,
+    375.15,
+    399.66,
+    368.5,
+    396.75,
+    362.75,
+    365.62,
+    336.59,
+    296.73,
+    407.69,
+    367.08,
+    376.76,
+    397.12,
+    384.8,
+    382.99,
+    408.25,
+    371.72,
+    397.41,
+    373.98,
+    388.78,
+    413.99,
+    362.47,
+    402.46,
+    358.68,
+    403.34,
+    387.12,
+    369.06,
+    426.5,
+    375.9,
+    341.06
+   ],
+   "gpu_pcie_rx_mb": [
+    0.62,
+    0.62,
+    0.67,
+    0.67,
+    0.67,
+    0.62,
+    0.62,
+    0.57,
+    0.62,
+    0.67,
+    0.71,
+    0.81,
+    0.81,
+    0.86,
+    0.81,
+    0.86,
+    0.81,
+    0.86,
+    0.76,
+    0.81,
+    0.86,
+    0.81,
+    0.95,
+    0.81,
+    0.86,
+    0.86,
+    0.86,
+    0.71,
+    7078.07,
+    5438.42,
+    7891.61,
+    5618.71,
+    5824.99,
+    6656.5,
+    6553.84,
+    1295.8,
+    3929.76,
+    0.67,
+    7089.76,
+    6013.73,
+    7916.07,
+    5803.39,
+    5749.08,
+    4295.01,
+    6229.4,
+    7158.52,
+    6448.94,
+    8972.07,
+    4133.89,
+    5762.81,
+    4218.58,
+    7081.13,
+    5446.96,
+    19399.45,
+    7164.1,
+    6657.41,
+    4340.22,
+    8272.65,
+    7551.43,
+    0.67
+   ],
+   "cpu": [
+    1.4,
+    3.7,
+    2.4,
+    2.6,
+    2.2,
+    1.6,
+    7.0,
+    7.8,
+    0.8,
+    3.8,
+    6.2,
+    1.4,
+    1.5,
+    1.3,
+    0.5,
+    0.8,
+    1.4,
+    1.7,
+    1.4,
+    1.5,
+    8.2,
+    9.2,
+    2.9,
+    5.7,
+    1.3,
+    5.6,
+    1.2,
+    7.3,
+    6.3,
+    9.1,
+    6.4,
+    7.4,
+    6.7,
+    6.4,
+    16.3,
+    9.8,
+    6.3,
+    19.7,
+    4.9,
+    6.7,
+    5.5,
+    6.3,
+    6.2,
+    6.4,
+    7.1,
+    6.3,
+    6.6,
+    6.4,
+    16.7,
+    8.7,
+    6.4,
+    6.7,
+    6.7,
+    6.4,
+    6.1,
+    7.1,
+    5.5,
+    9.0,
+    6.7,
+    16.5
+   ],
+   "ram_used": [
+    70616137728,
+    70634639360,
+    70632943616,
+    70619291648,
+    70622433280,
+    70624546816,
+    70651342848,
+    70754201600,
+    70754394112,
+    70772871168,
+    70811869184,
+    70806048768,
+    70788648960,
+    70775001088,
+    70770065408,
+    70761766912,
+    70762528768,
+    70758371328,
+    70767398912,
+    70768398336,
+    70723190784,
+    70684524544,
+    70713102336,
+    70694293504,
+    70656102400,
+    70685872128,
+    70679355392,
+    70251024384,
+    70250827776,
+    70240993280,
+    70217400320,
+    70216302592,
+    70220156928,
+    70211788800,
+    70218944512,
+    70240178176,
+    70232375296,
+    70472826880,
+    70432313344,
+    70401486848,
+    70392971264,
+    70382305280,
+    70365552640,
+    70356713472,
+    70348333056,
+    70341337088,
+    70134956032,
+    70120873984,
+    70109106176,
+    70101512192,
+    70084435968,
+    70076407808,
+    70066089984,
+    70059646976,
+    70027522048,
+    70087983104,
+    70087725056,
+    70115901440,
+    70239928320,
+    70477971456
+   ],
+   "disk_read_mb": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.04,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    1.46,
+    0.01,
+    0.0,
+    0.0,
+    0.82,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.2,
+    0.52,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.59,
+    0.0,
+    0.0,
+    0.02,
+    0.0,
+    0.04,
+    0.0,
+    0.0,
+    0.05,
+    0.0,
+    0.22,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.17
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790718941.76262
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-IQ3_S-2x3090-auto-needle/needle-28k-1.json

@@ -0,0 +1,764 @@
+{
+ "label": "native-v0.1.26-IQ3_S-2x3090-auto-needle",
+ "mode": "needle",
+ "ctx": "28k",
+ "target_tokens": 28672,
+ "run": 1,
+ "run_id": "c61aafff2d90",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:55:41",
+ "prompt_tokens": 29827,
+ "completion_tokens": 8,
+ "ttft_s": 39.958,
+ "e2e_s": 40.036,
+ "api_prompt_tps": 746.5,
+ "api_decode_tps": 89.7,
+ "engine_prompt_tps": 749.2,
+ "engine_decode_tps": 85.9,
+ "log_lines": [
+  "strata serve: prompt 29827 tokens = 0 reused + 29827 read in 39812 ms (749.2 tok/s), 8 generated in 93 ms (85.9 tok/s), drafts accepted 6 of 6, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 96.2% (4154 hits / 4318 lookups)"
+ ],
+ "answer_head": "7BDBA3C1",
+ "needle_found": true,
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-iq3_s",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 9376,
+   "expert_cache_mib": 17297,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 635,
+   "cvec": 0,
+   "arena_mib": 47962,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790718941.8879943,
+    "duration_s": 39.9,
+    "finish": "stop",
+    "prompt_tokens": 29827,
+    "reused": 0,
+    "output_tokens": 8,
+    "engine_generated": 8,
+    "prompt_ms": 39812.1,
+    "decode_ms": 93.1,
+    "decode_tok_s": 85.9,
+    "hit_rate": 0.962
+   },
+   {
+    "projection": null,
+    "time": 1790718917.8830457,
+    "duration_s": 23.4,
+    "finish": "stop",
+    "prompt_tokens": 17345,
+    "reused": 0,
+    "output_tokens": 8,
+    "engine_generated": 8,
+    "prompt_ms": 23292.2,
+    "decode_ms": 78.7,
+    "decode_tok_s": 101.7,
+    "hit_rate": 0.963
+   },
+   {
+    "projection": null,
+    "time": 1790718906.5660036,
+    "duration_s": 10.7,
+    "finish": "stop",
+    "prompt_tokens": 7491,
+    "reused": 0,
+    "output_tokens": 8,
+    "engine_generated": 8,
+    "prompt_ms": 10625.3,
+    "decode_ms": 109.4,
+    "decode_tok_s": 73.1,
+    "hit_rate": 0.902
+   },
+   {
+    "projection": null,
+    "time": 1790718828.4807332,
+    "duration_s": 42.6,
+    "finish": "stop",
+    "prompt_tokens": 31604,
+    "reused": 0,
+    "output_tokens": 49,
+    "engine_generated": 49,
+    "prompt_ms": 42110.8,
+    "decode_ms": 460.9,
+    "decode_tok_s": 106.3,
+    "hit_rate": 0.991
+   },
+   {
+    "projection": null,
+    "time": 1790718784.8375118,
+    "duration_s": 43.0,
+    "finish": "stop",
+    "prompt_tokens": 31633,
+    "reused": 0,
+    "output_tokens": 88,
+    "engine_generated": 88,
+    "prompt_ms": 42216.7,
+    "decode_ms": 776.7,
+    "decode_tok_s": 113.3,
+    "hit_rate": 0.978
+   },
+   {
+    "projection": null,
+    "time": 1790718743.8685048,
+    "duration_s": 40.3,
+    "finish": "stop",
+    "prompt_tokens": 28315,
+    "reused": 0,
+    "output_tokens": 84,
+    "engine_generated": 84,
+    "prompt_ms": 39286.5,
+    "decode_ms": 1011.1,
+    "decode_tok_s": 83.1,
+    "hit_rate": 0.949
+   }
+  ],
+  "requests_kept": 6,
+  "totals": {
+   "since": 1790718725.4039552,
+   "requests": 6,
+   "prompt_tokens": 146215,
+   "reused": 0,
+   "output_tokens": 245,
+   "prompt_ms": 197343.6,
+   "decode_ms": 2529.9
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 0,
+     "mem_used": 25212944384,
+     "mem_total": 25769803776,
+     "temp": 47,
+     "power": 130.942
+    },
+    {
+     "index": 1,
+     "util": 42,
+     "mem_used": 24227282944,
+     "mem_total": 25769803776,
+     "temp": 53,
+     "power": 227.639
+    }
+   ],
+   "gpu_util": 21.0,
+   "gpu_mem_used": 49440227328,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 53,
+   "gpu_power": 358.581,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 0.666015625,
+   "gpu_pcie_tx_mb": 0.857421875,
+   "cpu": 6.3,
+   "ram_used": 70479159296,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.0,
+   "disk_write_mb": 0.014414807554752778,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    0.5,
+    50.0,
+    34.5,
+    25.0,
+    60.5,
+    31.5,
+    26.0,
+    33.5,
+    46.5,
+    25.0,
+    31.5,
+    21.0,
+    30.0,
+    35.0,
+    37.0,
+    32.5,
+    22.0,
+    26.5,
+    19.5,
+    49.5,
+    26.5,
+    21.0,
+    2.5,
+    50.5,
+    42.0,
+    43.0,
+    38.0,
+    32.0,
+    21.5,
+    29.0,
+    34.0,
+    13.5,
+    36.0,
+    23.0,
+    30.0,
+    11.0,
+    77.5,
+    34.5,
+    23.5,
+    29.0,
+    17.5,
+    69.0,
+    34.5,
+    23.5,
+    32.5,
+    24.5,
+    57.5,
+    32.0,
+    26.0,
+    33.5,
+    25.0,
+    32.0,
+    32.5,
+    22.5,
+    36.0,
+    37.0,
+    36.5,
+    28.5,
+    42.5,
+    21.0
+   ],
+   "gpu_mem_used": [
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328
+   ],
+   "gpu_temp": [
+    50,
+    49,
+    49,
+    51,
+    52,
+    50,
+    52,
+    51,
+    51,
+    51,
+    51,
+    52,
+    51,
+    52,
+    51,
+    51,
+    52,
+    52,
+    51,
+    52,
+    52,
+    53,
+    51,
+    50,
+    50,
+    51,
+    53,
+    51,
+    52,
+    52,
+    51,
+    52,
+    51,
+    52,
+    52,
+    52,
+    53,
+    52,
+    52,
+    51,
+    51,
+    53,
+    52,
+    52,
+    52,
+    52,
+    52,
+    51,
+    53,
+    52,
+    52,
+    52,
+    52,
+    53,
+    52,
+    53,
+    52,
+    53,
+    52,
+    53
+   ],
+   "gpu_power": [
+    336.59,
+    296.73,
+    407.69,
+    367.08,
+    376.76,
+    397.12,
+    384.8,
+    382.99,
+    408.25,
+    371.72,
+    397.41,
+    373.98,
+    388.78,
+    413.99,
+    362.47,
+    402.46,
+    358.68,
+    403.34,
+    387.12,
+    369.06,
+    426.5,
+    375.9,
+    341.06,
+    316.12,
+    396.45,
+    370.14,
+    378.61,
+    411.6,
+    381.87,
+    383.44,
+    399.03,
+    378.32,
+    399.6,
+    372.43,
+    400.43,
+    390.19,
+    384.29,
+    405.22,
+    398.65,
+    405.33,
+    377.77,
+    347.82,
+    408.44,
+    395.16,
+    399.76,
+    391.18,
+    383.68,
+    395.97,
+    381.79,
+    371.58,
+    387.34,
+    367.36,
+    390.18,
+    377.99,
+    404.54,
+    406.77,
+    371.21,
+    404.91,
+    389.57,
+    358.58
+   ],
+   "gpu_pcie_rx_mb": [
+    0.67,
+    7089.76,
+    6013.73,
+    7916.07,
+    5803.39,
+    5749.08,
+    4295.01,
+    6229.4,
+    7158.52,
+    6448.94,
+    8972.07,
+    4133.89,
+    5762.81,
+    4218.58,
+    7081.13,
+    5446.96,
+    19399.45,
+    7164.1,
+    6657.41,
+    4340.22,
+    8272.65,
+    7551.43,
+    0.67,
+    5912.64,
+    6668.66,
+    4836.32,
+    15187.07,
+    6919.96,
+    7012.13,
+    4668.04,
+    8340.98,
+    5615.52,
+    6986.24,
+    8358.29,
+    8231.35,
+    7154.13,
+    6558.46,
+    5322.65,
+    14744.81,
+    6437.3,
+    7645.75,
+    4067.04,
+    5734.82,
+    1.62,
+    5507.04,
+    5994.7,
+    5715.7,
+    6093.12,
+    89.88,
+    6215.57,
+    4331.35,
+    6045.63,
+    5971.19,
+    6178.04,
+    5846.59,
+    7484.53,
+    5744.65,
+    5095.67,
+    7809.07,
+    0.67
+   ],
+   "cpu": [
+    19.7,
+    4.9,
+    6.7,
+    5.5,
+    6.3,
+    6.2,
+    6.4,
+    7.1,
+    6.3,
+    6.6,
+    6.4,
+    16.7,
+    8.7,
+    6.4,
+    6.7,
+    6.7,
+    6.4,
+    6.1,
+    7.1,
+    5.5,
+    9.0,
+    6.7,
+    16.5,
+    4.3,
+    8.5,
+    17.0,
+    10.5,
+    8.0,
+    8.5,
+    6.2,
+    6.8,
+    6.0,
+    6.0,
+    5.6,
+    6.4,
+    7.1,
+    5.6,
+    6.3,
+    11.3,
+    13.8,
+    13.6,
+    7.0,
+    5.8,
+    6.1,
+    6.1,
+    6.3,
+    6.2,
+    6.0,
+    9.3,
+    6.5,
+    6.1,
+    6.0,
+    14.5,
+    11.7,
+    5.6,
+    8.6,
+    7.7,
+    6.1,
+    6.7,
+    6.3
+   ],
+   "ram_used": [
+    70472826880,
+    70432313344,
+    70401486848,
+    70392971264,
+    70382305280,
+    70365552640,
+    70356713472,
+    70348333056,
+    70341337088,
+    70134956032,
+    70120873984,
+    70109106176,
+    70101512192,
+    70084435968,
+    70076407808,
+    70066089984,
+    70059646976,
+    70027522048,
+    70087983104,
+    70087725056,
+    70115901440,
+    70239928320,
+    70477971456,
+    70343557120,
+    70337265664,
+    70309584896,
+    70434922496,
+    70428250112,
+    70420987904,
+    70412926976,
+    70409207808,
+    70400454656,
+    70391336960,
+    70383079424,
+    70374731776,
+    70367465472,
+    70359465984,
+    70354010112,
+    70334316544,
+    70343401472,
+    70345613312,
+    70344155136,
+    70340018176,
+    70356168704,
+    70375772160,
+    70372450304,
+    70371860480,
+    70366474240,
+    70373842944,
+    70374035456,
+    70365605888,
+    70363926528,
+    70340509696,
+    70341251072,
+    70340546560,
+    70343122944,
+    70346379264,
+    70347120640,
+    70345048064,
+    70479159296
+   ],
+   "disk_read_mb": [
+    0.2,
+    0.52,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.59,
+    0.0,
+    0.0,
+    0.02,
+    0.0,
+    0.04,
+    0.0,
+    0.0,
+    0.05,
+    0.0,
+    0.22,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.17,
+    0.53,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.01,
+    0.0,
+    0.6,
+    0.0,
+    0.03,
+    0.0,
+    0.0,
+    0.05,
+    0.0,
+    0.0,
+    0.05,
+    0.0,
+    0.05,
+    0.0,
+    0.0,
+    0.03,
+    0.0,
+    0.04,
+    0.0,
+    0.0,
+    0.18,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790718982.302463
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-IQ3_S-2x3090-auto-needle/needle-8k-1.json

@@ -0,0 +1,736 @@
+{
+ "label": "native-v0.1.26-IQ3_S-2x3090-auto-needle",
+ "mode": "needle",
+ "ctx": "8k",
+ "target_tokens": 8192,
+ "run": 1,
+ "run_id": "7c040dd4c6d7",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:55:06",
+ "prompt_tokens": 7491,
+ "completion_tokens": 8,
+ "ttft_s": 10.682,
+ "e2e_s": 10.776,
+ "api_prompt_tps": 701.3,
+ "api_decode_tps": 74.7,
+ "engine_prompt_tps": 705.0,
+ "engine_decode_tps": 73.1,
+ "log_lines": [
+  "strata serve: prompt 7491 tokens = 0 reused + 7491 read in 10625 ms (705.0 tok/s), 8 generated in 109 ms (73.1 tok/s), drafts accepted 6 of 6, 1 checkpoints",
+  "strata serve: decode expert cache hit rate: 90.2% (3891 hits / 4313 lookups)"
+ ],
+ "answer_head": "C43C98BD",
+ "needle_found": true,
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-iq3_s",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 9376,
+   "expert_cache_mib": 17297,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 635,
+   "cvec": 0,
+   "arena_mib": 47962,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790718906.5660036,
+    "duration_s": 10.7,
+    "finish": "stop",
+    "prompt_tokens": 7491,
+    "reused": 0,
+    "output_tokens": 8,
+    "engine_generated": 8,
+    "prompt_ms": 10625.3,
+    "decode_ms": 109.4,
+    "decode_tok_s": 73.1,
+    "hit_rate": 0.902
+   },
+   {
+    "projection": null,
+    "time": 1790718828.4807332,
+    "duration_s": 42.6,
+    "finish": "stop",
+    "prompt_tokens": 31604,
+    "reused": 0,
+    "output_tokens": 49,
+    "engine_generated": 49,
+    "prompt_ms": 42110.8,
+    "decode_ms": 460.9,
+    "decode_tok_s": 106.3,
+    "hit_rate": 0.991
+   },
+   {
+    "projection": null,
+    "time": 1790718784.8375118,
+    "duration_s": 43.0,
+    "finish": "stop",
+    "prompt_tokens": 31633,
+    "reused": 0,
+    "output_tokens": 88,
+    "engine_generated": 88,
+    "prompt_ms": 42216.7,
+    "decode_ms": 776.7,
+    "decode_tok_s": 113.3,
+    "hit_rate": 0.978
+   },
+   {
+    "projection": null,
+    "time": 1790718743.8685048,
+    "duration_s": 40.3,
+    "finish": "stop",
+    "prompt_tokens": 28315,
+    "reused": 0,
+    "output_tokens": 84,
+    "engine_generated": 84,
+    "prompt_ms": 39286.5,
+    "decode_ms": 1011.1,
+    "decode_tok_s": 83.1,
+    "hit_rate": 0.949
+   }
+  ],
+  "requests_kept": 4,
+  "totals": {
+   "since": 1790718725.4039552,
+   "requests": 4,
+   "prompt_tokens": 99043,
+   "reused": 0,
+   "output_tokens": 229,
+   "prompt_ms": 134239.3,
+   "decode_ms": 2358.1000000000004
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 1,
+     "mem_used": 25212944384,
+     "mem_total": 25769803776,
+     "temp": 46,
+     "power": 122.865
+    },
+    {
+     "index": 1,
+     "util": 0,
+     "mem_used": 24227282944,
+     "mem_total": 25769803776,
+     "temp": 50,
+     "power": 213.727
+    }
+   ],
+   "gpu_util": 0.5,
+   "gpu_mem_used": 49440227328,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 50,
+   "gpu_power": 336.592,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 0.666015625,
+   "gpu_pcie_tx_mb": 0.9052734375,
+   "cpu": 19.7,
+   "ram_used": 70472826880,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.2018157842351215,
+   "disk_write_mb": 0.28470440990311785,
+   "tok_s": 0.0,
+   "tok_s_mean": 0.0
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    25.0,
+    33.5,
+    47.0,
+    15.5,
+    32.5,
+    24.0,
+    32.5,
+    29.0,
+    55.0,
+    34.0,
+    48.0,
+    33.0,
+    22.5,
+    31.5,
+    24.5,
+    20.0,
+    20.5,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    37.0,
+    28.0,
+    22.5,
+    30.0,
+    37.0,
+    18.0,
+    29.0,
+    22.0,
+    21.0,
+    0.5
+   ],
+   "gpu_mem_used": [
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328
+   ],
+   "gpu_temp": [
+    51,
+    50,
+    51,
+    51,
+    51,
+    51,
+    51,
+    51,
+    51,
+    50,
+    52,
+    52,
+    52,
+    51,
+    52,
+    52,
+    50,
+    49,
+    49,
+    49,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    48,
+    45,
+    45,
+    45,
+    45,
+    45,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    44,
+    50,
+    49,
+    51,
+    51,
+    51,
+    51,
+    50,
+    51,
+    52,
+    50
+   ],
+   "gpu_power": [
+    380.19,
+    386.69,
+    409.76,
+    359.41,
+    400.68,
+    368.54,
+    396.07,
+    393.99,
+    371.52,
+    407.92,
+    367.65,
+    416.33,
+    386.19,
+    394.79,
+    409.75,
+    373.56,
+    329.84,
+    371.48,
+    309.69,
+    279.06,
+    254.32,
+    242.47,
+    242.53,
+    242.44,
+    242.38,
+    242.52,
+    242.49,
+    242.46,
+    242.59,
+    242.37,
+    242.36,
+    242.5,
+    242.54,
+    140.5,
+    84.6,
+    65.59,
+    65.03,
+    64.81,
+    64.81,
+    64.9,
+    64.51,
+    64.65,
+    64.87,
+    64.67,
+    64.8,
+    64.5,
+    64.56,
+    64.64,
+    64.52,
+    64.48,
+    252.37,
+    388.02,
+    363.78,
+    375.15,
+    399.66,
+    368.5,
+    396.75,
+    362.75,
+    365.62,
+    336.59
+   ],
+   "gpu_pcie_rx_mb": [
+    5368.61,
+    7806.78,
+    7675.93,
+    8469.58,
+    5669.88,
+    14723.06,
+    5790.85,
+    6188.01,
+    6980.23,
+    7332.23,
+    12898.87,
+    6754.21,
+    6340.74,
+    6000.61,
+    6420.09,
+    4455.66,
+    19.74,
+    0.62,
+    0.62,
+    0.57,
+    0.67,
+    0.62,
+    0.62,
+    0.62,
+    0.67,
+    0.67,
+    0.67,
+    0.62,
+    0.62,
+    0.57,
+    0.62,
+    0.67,
+    0.71,
+    0.81,
+    0.81,
+    0.86,
+    0.81,
+    0.86,
+    0.81,
+    0.86,
+    0.76,
+    0.81,
+    0.86,
+    0.81,
+    0.95,
+    0.81,
+    0.86,
+    0.86,
+    0.86,
+    0.71,
+    7078.07,
+    5438.42,
+    7891.61,
+    5618.71,
+    5824.99,
+    6656.5,
+    6553.84,
+    1295.8,
+    3929.76,
+    0.67
+   ],
+   "cpu": [
+    7.3,
+    17.5,
+    8.0,
+    7.9,
+    6.6,
+    6.2,
+    6.2,
+    6.1,
+    6.6,
+    5.7,
+    6.8,
+    7.1,
+    7.8,
+    6.2,
+    9.8,
+    15.0,
+    32.2,
+    20.2,
+    4.3,
+    11.3,
+    2.0,
+    1.5,
+    1.4,
+    3.7,
+    2.4,
+    2.6,
+    2.2,
+    1.6,
+    7.0,
+    7.8,
+    0.8,
+    3.8,
+    6.2,
+    1.4,
+    1.5,
+    1.3,
+    0.5,
+    0.8,
+    1.4,
+    1.7,
+    1.4,
+    1.5,
+    8.2,
+    9.2,
+    2.9,
+    5.7,
+    1.3,
+    5.6,
+    1.2,
+    7.3,
+    6.3,
+    9.1,
+    6.4,
+    7.4,
+    6.7,
+    6.4,
+    16.3,
+    9.8,
+    6.3,
+    19.7
+   ],
+   "ram_used": [
+    70159552512,
+    70270476288,
+    70270668800,
+    70271184896,
+    70263926784,
+    70264184832,
+    70264291328,
+    70265167872,
+    70267035648,
+    70267035648,
+    70264389632,
+    70261067776,
+    70265782272,
+    70268100608,
+    70275043328,
+    70091866112,
+    70312075264,
+    70311395328,
+    70465576960,
+    70613889024,
+    70610006016,
+    70609461248,
+    70616137728,
+    70634639360,
+    70632943616,
+    70619291648,
+    70622433280,
+    70624546816,
+    70651342848,
+    70754201600,
+    70754394112,
+    70772871168,
+    70811869184,
+    70806048768,
+    70788648960,
+    70775001088,
+    70770065408,
+    70761766912,
+    70762528768,
+    70758371328,
+    70767398912,
+    70768398336,
+    70723190784,
+    70684524544,
+    70713102336,
+    70694293504,
+    70656102400,
+    70685872128,
+    70679355392,
+    70251024384,
+    70250827776,
+    70240993280,
+    70217400320,
+    70216302592,
+    70220156928,
+    70211788800,
+    70218944512,
+    70240178176,
+    70232375296,
+    70472826880
+   ],
+   "disk_read_mb": [
+    0.0,
+    0.04,
+    0.0,
+    0.01,
+    0.0,
+    0.02,
+    0.0,
+    0.0,
+    0.01,
+    0.0,
+    0.22,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.09,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.04,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    1.46,
+    0.01,
+    0.0,
+    0.0,
+    0.82,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.2
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    97.75,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ]
+  },
+  "time": 1790718917.804988
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-IQ3_S-2x3090-auto-two-turn/two-turn-16k-1.json

@@ -0,0 +1,797 @@
+{
+ "label": "native-v0.1.26-IQ3_S-2x3090-auto-two-turn",
+ "mode": "two-turn",
+ "ctx": "16k",
+ "target_tokens": 16384,
+ "run": 1,
+ "run_id": "2fd93144a29a",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:56:47",
+ "prompt_tokens": 15639,
+ "completion_tokens": 83,
+ "ttft_s": 21.242,
+ "e2e_s": 22.071,
+ "api_prompt_tps": 736.2,
+ "api_decode_tps": 98.8,
+ "engine_prompt_tps": 739.4,
+ "engine_decode_tps": 98.3,
+ "log_lines": [
+  "strata serve: prompt 15639 tokens = 0 reused + 15639 read in 21151 ms (739.4 tok/s), 83 generated in 844 ms (98.3 tok/s), drafts accepted 53 of 73, 1 checkpoints",
+  "strata serve: decode expert cache hit rate: 98.5% (48689 hits / 49415 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what's there.",
+ "turn2_ttft_s": 0.627,
+ "turn2_prompt_tokens": 15676,
+ "turn2_log_lines": [
+  "strata serve: prompt 15676 tokens = 15632 reused + 44 read in 521 ms (84.4 tok/s), 64 generated in 739 ms (86.6 tok/s), drafts accepted 37 of 52, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 97.1% (36768 hits / 37868 lookups)"
+ ],
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-iq3_s",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 9376,
+   "expert_cache_mib": 17297,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 635,
+   "cvec": 0,
+   "arena_mib": 47962,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790719030.332211,
+    "duration_s": 1.3,
+    "finish": "length",
+    "prompt_tokens": 15676,
+    "reused": 15632,
+    "output_tokens": 64,
+    "engine_generated": 64,
+    "prompt_ms": 521.0,
+    "decode_ms": 739.1,
+    "decode_tok_s": 86.6,
+    "hit_rate": 0.971
+   },
+   {
+    "projection": null,
+    "time": 1790719007.7458334,
+    "duration_s": 22.0,
+    "finish": "stop",
+    "prompt_tokens": 15639,
+    "reused": 0,
+    "output_tokens": 83,
+    "engine_generated": 83,
+    "prompt_ms": 21150.9,
+    "decode_ms": 844.3,
+    "decode_tok_s": 98.3,
+    "hit_rate": 0.985
+   },
+   {
+    "projection": null,
+    "time": 1790718941.8879943,
+    "duration_s": 39.9,
+    "finish": "stop",
+    "prompt_tokens": 29827,
+    "reused": 0,
+    "output_tokens": 8,
+    "engine_generated": 8,
+    "prompt_ms": 39812.1,
+    "decode_ms": 93.1,
+    "decode_tok_s": 85.9,
+    "hit_rate": 0.962
+   },
+   {
+    "projection": null,
+    "time": 1790718917.8830457,
+    "duration_s": 23.4,
+    "finish": "stop",
+    "prompt_tokens": 17345,
+    "reused": 0,
+    "output_tokens": 8,
+    "engine_generated": 8,
+    "prompt_ms": 23292.2,
+    "decode_ms": 78.7,
+    "decode_tok_s": 101.7,
+    "hit_rate": 0.963
+   },
+   {
+    "projection": null,
+    "time": 1790718906.5660036,
+    "duration_s": 10.7,
+    "finish": "stop",
+    "prompt_tokens": 7491,
+    "reused": 0,
+    "output_tokens": 8,
+    "engine_generated": 8,
+    "prompt_ms": 10625.3,
+    "decode_ms": 109.4,
+    "decode_tok_s": 73.1,
+    "hit_rate": 0.902
+   },
+   {
+    "projection": null,
+    "time": 1790718828.4807332,
+    "duration_s": 42.6,
+    "finish": "stop",
+    "prompt_tokens": 31604,
+    "reused": 0,
+    "output_tokens": 49,
+    "engine_generated": 49,
+    "prompt_ms": 42110.8,
+    "decode_ms": 460.9,
+    "decode_tok_s": 106.3,
+    "hit_rate": 0.991
+   },
+   {
+    "projection": null,
+    "time": 1790718784.8375118,
+    "duration_s": 43.0,
+    "finish": "stop",
+    "prompt_tokens": 31633,
+    "reused": 0,
+    "output_tokens": 88,
+    "engine_generated": 88,
+    "prompt_ms": 42216.7,
+    "decode_ms": 776.7,
+    "decode_tok_s": 113.3,
+    "hit_rate": 0.978
+   },
+   {
+    "projection": null,
+    "time": 1790718743.8685048,
+    "duration_s": 40.3,
+    "finish": "stop",
+    "prompt_tokens": 28315,
+    "reused": 0,
+    "output_tokens": 84,
+    "engine_generated": 84,
+    "prompt_ms": 39286.5,
+    "decode_ms": 1011.1,
+    "decode_tok_s": 83.1,
+    "hit_rate": 0.949
+   }
+  ],
+  "requests_kept": 8,
+  "totals": {
+   "since": 1790718725.4039552,
+   "requests": 8,
+   "prompt_tokens": 177530,
+   "reused": 15632,
+   "output_tokens": 392,
+   "prompt_ms": 219015.5,
+   "decode_ms": 4113.3
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 41,
+     "mem_used": 25212944384,
+     "mem_total": 25769803776,
+     "temp": 50,
+     "power": 209.466
+    },
+    {
+     "index": 1,
+     "util": 49,
+     "mem_used": 24227282944,
+     "mem_total": 25769803776,
+     "temp": 53,
+     "power": 186.867
+    }
+   ],
+   "gpu_util": 45.0,
+   "gpu_mem_used": 49440227328,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 53,
+   "gpu_power": 396.33299999999997,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 2090.7392578125,
+   "gpu_pcie_tx_mb": 103.1865234375,
+   "cpu": 82.0,
+   "ram_used": 70765735936,
+   "ram_total": 177175990272,
+   "disk_read_mb": 3.548661248401337,
+   "disk_write_mb": 0.003595401467478558,
+   "tok_s": 85.02069488627261,
+   "tok_s_mean": 85.60127593635436
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    57.5,
+    32.0,
+    26.0,
+    33.5,
+    25.0,
+    32.0,
+    32.5,
+    22.5,
+    36.0,
+    37.0,
+    36.5,
+    28.5,
+    42.5,
+    21.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    32.0,
+    30.5,
+    25.5,
+    63.5,
+    34.5,
+    24.5,
+    36.0,
+    38.0,
+    28.0,
+    33.0,
+    21.5,
+    25.0,
+    41.5,
+    33.0,
+    30.0,
+    22.0,
+    29.5,
+    19.5,
+    23.5,
+    48.0,
+    0.0,
+    45.0
+   ],
+   "gpu_mem_used": [
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328
+   ],
+   "gpu_temp": [
+    52,
+    51,
+    53,
+    52,
+    52,
+    52,
+    52,
+    53,
+    52,
+    53,
+    52,
+    53,
+    52,
+    53,
+    51,
+    50,
+    49,
+    49,
+    49,
+    49,
+    49,
+    49,
+    49,
+    49,
+    49,
+    49,
+    49,
+    49,
+    49,
+    49,
+    47,
+    46,
+    46,
+    46,
+    46,
+    45,
+    45,
+    45,
+    51,
+    51,
+    51,
+    52,
+    51,
+    53,
+    52,
+    53,
+    52,
+    52,
+    53,
+    52,
+    53,
+    52,
+    52,
+    53,
+    53,
+    53,
+    53,
+    53,
+    51,
+    53
+   ],
+   "gpu_power": [
+    383.68,
+    395.97,
+    381.79,
+    371.58,
+    387.34,
+    367.36,
+    390.18,
+    377.99,
+    404.54,
+    406.77,
+    371.21,
+    404.91,
+    389.57,
+    358.58,
+    310.16,
+    278.39,
+    242.88,
+    242.69,
+    242.56,
+    242.41,
+    242.25,
+    242.45,
+    242.44,
+    242.38,
+    242.25,
+    242.18,
+    242.52,
+    242.57,
+    242.25,
+    242.23,
+    197.61,
+    110.58,
+    65.55,
+    65.12,
+    65.0,
+    65.02,
+    65.01,
+    64.82,
+    155.28,
+    410.36,
+    361.72,
+    382.57,
+    404.0,
+    377.89,
+    389.35,
+    407.89,
+    389.48,
+    386.49,
+    371.41,
+    379.85,
+    411.79,
+    387.4,
+    395.89,
+    369.99,
+    400.03,
+    390.77,
+    393.61,
+    354.25,
+    413.98,
+    396.33
+   ],
+   "gpu_pcie_rx_mb": [
+    5715.7,
+    6093.12,
+    89.88,
+    6215.57,
+    4331.35,
+    6045.63,
+    5971.19,
+    6178.04,
+    5846.59,
+    7484.53,
+    5744.65,
+    5095.67,
+    7809.07,
+    0.67,
+    0.71,
+    0.57,
+    0.67,
+    0.62,
+    0.62,
+    0.57,
+    0.71,
+    0.62,
+    0.57,
+    0.67,
+    0.62,
+    0.62,
+    0.57,
+    0.62,
+    0.62,
+    0.71,
+    0.91,
+    0.81,
+    0.76,
+    0.81,
+    0.76,
+    0.81,
+    0.86,
+    0.86,
+    6219.24,
+    5437.52,
+    6447.08,
+    6610.58,
+    6506.2,
+    88.93,
+    6106.14,
+    6218.53,
+    5297.85,
+    8021.88,
+    67.85,
+    4886.82,
+    6395.77,
+    5794.95,
+    5961.99,
+    92.79,
+    4561.42,
+    5886.93,
+    4115.39,
+    15.07,
+    6036.38,
+    2090.74
+   ],
+   "cpu": [
+    6.2,
+    6.0,
+    9.3,
+    6.5,
+    6.1,
+    6.0,
+    14.5,
+    11.7,
+    5.6,
+    8.6,
+    7.7,
+    6.1,
+    6.7,
+    6.3,
+    15.2,
+    4.0,
+    11.7,
+    1.7,
+    0.8,
+    1.6,
+    10.1,
+    8.8,
+    1.8,
+    3.0,
+    2.0,
+    1.1,
+    3.9,
+    2.5,
+    1.2,
+    1.0,
+    4.4,
+    2.2,
+    2.1,
+    1.1,
+    9.2,
+    4.0,
+    0.7,
+    12.8,
+    6.2,
+    7.1,
+    6.6,
+    6.1,
+    5.7,
+    6.8,
+    7.9,
+    5.9,
+    6.1,
+    7.1,
+    16.6,
+    14.8,
+    6.4,
+    6.7,
+    6.6,
+    7.0,
+    6.5,
+    7.1,
+    6.4,
+    44.5,
+    46.9,
+    82.0
+   ],
+   "ram_used": [
+    70371860480,
+    70366474240,
+    70373842944,
+    70374035456,
+    70365605888,
+    70363926528,
+    70340509696,
+    70341251072,
+    70340546560,
+    70343122944,
+    70346379264,
+    70347120640,
+    70345048064,
+    70479159296,
+    70572703744,
+    70652428288,
+    70736793600,
+    70729584640,
+    70733873152,
+    70729728000,
+    70753632256,
+    70894960640,
+    70882795520,
+    70887088128,
+    70877409280,
+    70896922624,
+    70917816320,
+    70944993280,
+    70949908480,
+    70948433920,
+    70969233408,
+    70968532992,
+    70973911040,
+    70965530624,
+    70981591040,
+    70982193152,
+    70979321856,
+    71007891456,
+    70533447680,
+    70536957952,
+    70444630016,
+    70438658048,
+    70435995648,
+    70428848128,
+    70422986752,
+    70424240128,
+    70404268032,
+    70411444224,
+    70518763520,
+    70541369344,
+    70539395072,
+    70538240000,
+    70528540672,
+    70514954240,
+    70316679168,
+    70304641024,
+    70310481920,
+    70539440128,
+    70546964480,
+    70765735936
+   ],
+   "disk_read_mb": [
+    0.05,
+    0.0,
+    0.0,
+    0.03,
+    0.0,
+    0.04,
+    0.0,
+    0.0,
+    0.18,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.15,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.48,
+    0.01,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.02,
+    0.0,
+    0.01,
+    0.0,
+    0.03,
+    0.0,
+    0.0,
+    0.21,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.21,
+    0.47,
+    3.55
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    106.42,
+    0.0,
+    85.02
+   ]
+  },
+  "time": 1790719032.1000419
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-IQ3_S-2x3090-auto/speed-32k-1.json

@@ -0,0 +1,648 @@
+{
+ "label": "native-v0.1.26-IQ3_S-2x3090-auto",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 1,
+ "run_id": "e13c9cdd6797",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:52:23",
+ "prompt_tokens": 28315,
+ "completion_tokens": 84,
+ "ttft_s": 39.45,
+ "e2e_s": 40.422,
+ "api_prompt_tps": 717.7,
+ "api_decode_tps": 85.4,
+ "engine_prompt_tps": 720.7,
+ "engine_decode_tps": 83.1,
+ "log_lines": [
+  "strata serve: prompt 28315 tokens = 0 reused + 28315 read in 39287 ms (720.7 tok/s), 84 generated in 1011 ms (83.1 tok/s), drafts accepted 56 of 67, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 94.9% (43073 hits / 45377 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand the context and find the relevant files.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-iq3_s",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 9376,
+   "expert_cache_mib": 17297,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 635,
+   "cvec": 0,
+   "arena_mib": 47962,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790718743.8685048,
+    "duration_s": 40.3,
+    "finish": "stop",
+    "prompt_tokens": 28315,
+    "reused": 0,
+    "output_tokens": 84,
+    "engine_generated": 84,
+    "prompt_ms": 39286.5,
+    "decode_ms": 1011.1,
+    "decode_tok_s": 83.1,
+    "hit_rate": 0.949
+   }
+  ],
+  "requests_kept": 1,
+  "totals": {
+   "since": 1790718725.4039552,
+   "requests": 1,
+   "prompt_tokens": 28315,
+   "reused": 0,
+   "output_tokens": 84,
+   "prompt_ms": 39286.5,
+   "decode_ms": 1011.1
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 39,
+     "mem_used": 25212944384,
+     "mem_total": 25769803776,
+     "temp": 45,
+     "power": 141.739
+    },
+    {
+     "index": 1,
+     "util": 48,
+     "mem_used": 24227282944,
+     "mem_total": 25769803776,
+     "temp": 50,
+     "power": 205.268
+    }
+   ],
+   "gpu_util": 43.5,
+   "gpu_mem_used": 49440227328,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 50,
+   "gpu_power": 347.007,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 6170.3671875,
+   "gpu_pcie_tx_mb": 126.7900390625,
+   "cpu": 85.9,
+   "ram_used": 70739390464,
+   "ram_total": 177175990272,
+   "disk_read_mb": 3.315986845192439,
+   "disk_write_mb": 0.09340808014626588,
+   "tok_s": 93.51552437654362,
+   "tok_s_mean": 85.24938371584437
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    1.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    1.0,
+    57.0,
+    32.5,
+    23.5,
+    25.0,
+    22.0,
+    51.0,
+    35.5,
+    33.0,
+    27.5,
+    26.0,
+    41.0,
+    33.0,
+    23.5,
+    29.5,
+    27.5,
+    71.0,
+    31.5,
+    21.5,
+    64.0,
+    36.5,
+    20.5,
+    32.5,
+    30.5,
+    22.0,
+    29.0,
+    24.5,
+    30.0,
+    17.5,
+    76.0,
+    25.0,
+    20.5,
+    30.0,
+    23.0,
+    19.0,
+    24.0,
+    43.5
+   ],
+   "gpu_mem_used": [
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49224220672,
+    49316495360,
+    49326981120,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49440227328
+   ],
+   "gpu_temp": [
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    45,
+    42,
+    44,
+    47,
+    46,
+    49,
+    47,
+    49,
+    49,
+    49,
+    49,
+    48,
+    49,
+    48,
+    48,
+    49,
+    48,
+    48,
+    50,
+    48,
+    48,
+    48,
+    48,
+    49,
+    48,
+    48,
+    49,
+    48,
+    50,
+    49,
+    49,
+    51,
+    48,
+    50,
+    48,
+    49,
+    50,
+    50,
+    50
+   ],
+   "gpu_power": [
+    239.92,
+    240.19,
+    239.81,
+    239.35,
+    239.3,
+    239.28,
+    239.24,
+    239.29,
+    239.41,
+    239.46,
+    239.45,
+    239.36,
+    239.21,
+    239.26,
+    239.32,
+    239.37,
+    225.06,
+    145.42,
+    158.12,
+    371.86,
+    384.05,
+    358.93,
+    405.61,
+    381.25,
+    384.16,
+    389.93,
+    395.3,
+    399.41,
+    384.35,
+    363.41,
+    386.79,
+    392.7,
+    344.05,
+    389.76,
+    383.66,
+    397.8,
+    373.05,
+    366.9,
+    391.72,
+    366.3,
+    381.76,
+    387.41,
+    366.67,
+    395.88,
+    403.84,
+    386.94,
+    392.83,
+    352.42,
+    402.48,
+    392.8,
+    357.94,
+    383.58,
+    359.24,
+    350.73,
+    347.01
+   ],
+   "gpu_pcie_rx_mb": [
+    0.62,
+    0.67,
+    0.67,
+    0.62,
+    0.62,
+    0.57,
+    0.57,
+    0.57,
+    0.62,
+    0.67,
+    0.67,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.62,
+    0.76,
+    14.92,
+    6198.41,
+    7236.0,
+    8724.26,
+    3654.86,
+    5959.32,
+    6449.94,
+    6329.34,
+    7285.26,
+    4763.84,
+    6812.52,
+    7321.69,
+    6494.14,
+    5619.86,
+    6789.97,
+    5793.67,
+    5562.64,
+    2331.69,
+    6177.52,
+    8354.0,
+    7435.75,
+    4811.38,
+    1.43,
+    7506.18,
+    7562.16,
+    2886.44,
+    7184.17,
+    6752.54,
+    7546.95,
+    7499.69,
+    4610.3,
+    6852.1,
+    6167.22,
+    5107.31,
+    7326.55,
+    4237.65,
+    0.67,
+    6170.37
+   ],
+   "cpu": [
+    100.0,
+    1.4,
+    1.1,
+    0.9,
+    1.2,
+    2.3,
+    0.9,
+    1.3,
+    9.5,
+    5.4,
+    6.6,
+    4.7,
+    1.3,
+    1.2,
+    1.8,
+    2.0,
+    0.8,
+    11.3,
+    10.6,
+    10.4,
+    5.7,
+    6.8,
+    17.0,
+    10.2,
+    8.1,
+    7.1,
+    6.9,
+    7.6,
+    9.8,
+    9.9,
+    5.8,
+    6.7,
+    11.0,
+    6.0,
+    9.4,
+    6.2,
+    15.2,
+    12.9,
+    8.4,
+    7.2,
+    10.2,
+    6.1,
+    10.5,
+    6.4,
+    6.0,
+    9.0,
+    7.4,
+    8.9,
+    6.9,
+    8.7,
+    15.6,
+    12.0,
+    6.3,
+    6.8,
+    85.9
+   ],
+   "ram_used": [
+    70239571968,
+    70088245248,
+    70096302080,
+    70097154048,
+    70103457792,
+    70078648320,
+    70084857856,
+    70088122368,
+    70148214784,
+    70162341888,
+    70191161344,
+    70190673920,
+    70184566784,
+    70184079360,
+    70179979264,
+    70173462528,
+    70171906048,
+    70119723008,
+    70266146816,
+    70263320576,
+    70263308288,
+    70262693888,
+    70372823040,
+    70378594304,
+    70380400640,
+    70383910912,
+    70389587968,
+    70366543872,
+    70385344512,
+    70382903296,
+    70379986944,
+    70372298752,
+    70358667264,
+    70367678464,
+    70356070400,
+    70353756160,
+    70321405952,
+    70284603392,
+    70262280192,
+    70387703808,
+    70314864640,
+    70312120320,
+    70299967488,
+    70299987968,
+    70294355968,
+    70301368320,
+    70293327872,
+    70290792448,
+    70280925184,
+    70300200960,
+    70377836544,
+    70448394240,
+    70448910336,
+    70574612480,
+    70739390464
+   ],
+   "disk_read_mb": [
+    null,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.01,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    4.75,
+    124.76,
+    40.78,
+    0.0,
+    7.5,
+    16.84,
+    0.0,
+    55.72,
+    0.0,
+    13.03,
+    20.5,
+    0.0,
+    67.32,
+    0.0,
+    0.0,
+    83.74,
+    0.0,
+    80.89,
+    0.0,
+    0.0,
+    71.3,
+    0.0,
+    0.0,
+    79.43,
+    0.0,
+    72.4,
+    4.53,
+    0.0,
+    54.62,
+    0.0,
+    42.73,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    3.32
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    93.52
+   ]
+  },
+  "time": 1790718784.6773934
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-IQ3_S-2x3090-auto/speed-32k-2.json

@@ -0,0 +1,707 @@
+{
+ "label": "native-v0.1.26-IQ3_S-2x3090-auto",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 2,
+ "run_id": "f953f67441b4",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:53:04",
+ "prompt_tokens": 31633,
+ "completion_tokens": 88,
+ "ttft_s": 42.403,
+ "e2e_s": 43.165,
+ "api_prompt_tps": 746.0,
+ "api_decode_tps": 114.2,
+ "engine_prompt_tps": 749.3,
+ "engine_decode_tps": 113.3,
+ "log_lines": [
+  "strata serve: prompt 31633 tokens = 0 reused + 31633 read in 42217 ms (749.3 tok/s), 88 generated in 777 ms (113.3 tok/s), drafts accepted 61 of 69, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 97.8% (45031 hits / 46048 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what's there and identify the \"last file\" being referenced.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-iq3_s",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 9376,
+   "expert_cache_mib": 17297,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 635,
+   "cvec": 0,
+   "arena_mib": 47962,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790718784.8375118,
+    "duration_s": 43.0,
+    "finish": "stop",
+    "prompt_tokens": 31633,
+    "reused": 0,
+    "output_tokens": 88,
+    "engine_generated": 88,
+    "prompt_ms": 42216.7,
+    "decode_ms": 776.7,
+    "decode_tok_s": 113.3,
+    "hit_rate": 0.978
+   },
+   {
+    "projection": null,
+    "time": 1790718743.8685048,
+    "duration_s": 40.3,
+    "finish": "stop",
+    "prompt_tokens": 28315,
+    "reused": 0,
+    "output_tokens": 84,
+    "engine_generated": 84,
+    "prompt_ms": 39286.5,
+    "decode_ms": 1011.1,
+    "decode_tok_s": 83.1,
+    "hit_rate": 0.949
+   }
+  ],
+  "requests_kept": 2,
+  "totals": {
+   "since": 1790718725.4039552,
+   "requests": 2,
+   "prompt_tokens": 59948,
+   "reused": 0,
+   "output_tokens": 172,
+   "prompt_ms": 81503.2,
+   "decode_ms": 1787.8000000000002
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 43,
+     "mem_used": 25212944384,
+     "mem_total": 25769803776,
+     "temp": 46,
+     "power": 127.404
+    },
+    {
+     "index": 1,
+     "util": 22,
+     "mem_used": 24227282944,
+     "mem_total": 25769803776,
+     "temp": 50,
+     "power": 202.736
+    }
+   ],
+   "gpu_util": 32.5,
+   "gpu_mem_used": 49440227328,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 50,
+   "gpu_power": 330.14,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 50.97265625,
+   "gpu_pcie_tx_mb": 74.43359375,
+   "cpu": 47.4,
+   "ram_used": 70762872832,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.9085358249169909,
+   "disk_write_mb": 0.21546304148229034,
+   "tok_s": 110.51273259801776,
+   "tok_s_mean": 104.51731108020398
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    31.5,
+    21.5,
+    64.0,
+    36.5,
+    20.5,
+    32.5,
+    30.5,
+    22.0,
+    29.0,
+    24.5,
+    30.0,
+    17.5,
+    76.0,
+    25.0,
+    20.5,
+    30.0,
+    23.0,
+    19.0,
+    24.0,
+    43.5,
+    0.0,
+    41.5,
+    33.5,
+    27.5,
+    34.0,
+    22.0,
+    61.5,
+    37.0,
+    23.5,
+    24.5,
+    28.5,
+    54.0,
+    41.5,
+    89.5,
+    30.5,
+    21.0,
+    32.0,
+    33.5,
+    24.5,
+    26.0,
+    25.5,
+    38.5,
+    31.5,
+    24.5,
+    30.0,
+    26.0,
+    31.5,
+    19.0,
+    86.5,
+    28.0,
+    22.5,
+    32.0,
+    26.0,
+    77.5,
+    22.5,
+    22.5,
+    34.0,
+    26.0,
+    20.5,
+    32.5
+   ],
+   "gpu_mem_used": [
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49333272576,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328
+   ],
+   "gpu_temp": [
+    48,
+    48,
+    48,
+    48,
+    49,
+    48,
+    48,
+    49,
+    48,
+    50,
+    49,
+    49,
+    51,
+    48,
+    50,
+    48,
+    49,
+    50,
+    50,
+    50,
+    47,
+    48,
+    48,
+    50,
+    49,
+    50,
+    49,
+    49,
+    50,
+    49,
+    50,
+    49,
+    50,
+    51,
+    49,
+    50,
+    50,
+    49,
+    50,
+    50,
+    51,
+    50,
+    49,
+    50,
+    49,
+    51,
+    49,
+    50,
+    51,
+    49,
+    50,
+    50,
+    51,
+    52,
+    50,
+    50,
+    50,
+    51,
+    52,
+    50
+   ],
+   "gpu_power": [
+    397.8,
+    373.05,
+    366.9,
+    391.72,
+    366.3,
+    381.76,
+    387.41,
+    366.67,
+    395.88,
+    403.84,
+    386.94,
+    392.83,
+    352.42,
+    402.48,
+    392.8,
+    357.94,
+    383.58,
+    359.24,
+    350.73,
+    347.01,
+    325.66,
+    372.55,
+    370.97,
+    352.05,
+    397.27,
+    391.66,
+    343.17,
+    403.13,
+    366.16,
+    402.14,
+    390.68,
+    396.82,
+    401.28,
+    360.7,
+    398.3,
+    366.48,
+    382.49,
+    395.03,
+    366.16,
+    401.29,
+    385.57,
+    368.88,
+    396.03,
+    374.4,
+    393.23,
+    385.24,
+    406.68,
+    391.86,
+    364.28,
+    409.58,
+    388.38,
+    389.1,
+    390.65,
+    372.81,
+    415.25,
+    390.44,
+    384.85,
+    382.05,
+    377.98,
+    330.14
+   ],
+   "gpu_pcie_rx_mb": [
+    6177.52,
+    8354.0,
+    7435.75,
+    4811.38,
+    1.43,
+    7506.18,
+    7562.16,
+    2886.44,
+    7184.17,
+    6752.54,
+    7546.95,
+    7499.69,
+    4610.3,
+    6852.1,
+    6167.22,
+    5107.31,
+    7326.55,
+    4237.65,
+    0.67,
+    6170.37,
+    5107.54,
+    5192.28,
+    6336.26,
+    3422.45,
+    4911.8,
+    7759.14,
+    6146.0,
+    4671.1,
+    9668.92,
+    5712.17,
+    6061.89,
+    4888.06,
+    5886.08,
+    9090.42,
+    5683.33,
+    6294.68,
+    7625.39,
+    4995.82,
+    12979.6,
+    4392.43,
+    6062.41,
+    5581.95,
+    5691.53,
+    8234.83,
+    8344.89,
+    7880.73,
+    6094.07,
+    8294.58,
+    5858.85,
+    5465.17,
+    6922.82,
+    4432.29,
+    6296.59,
+    5837.44,
+    7103.97,
+    7604.84,
+    4756.35,
+    4899.02,
+    5517.96,
+    50.97
+   ],
+   "cpu": [
+    6.2,
+    15.2,
+    12.9,
+    8.4,
+    7.2,
+    10.2,
+    6.1,
+    10.5,
+    6.4,
+    6.0,
+    9.0,
+    7.4,
+    8.9,
+    6.9,
+    8.7,
+    15.6,
+    12.0,
+    6.3,
+    6.8,
+    85.9,
+    9.8,
+    9.7,
+    6.7,
+    6.6,
+    6.8,
+    7.4,
+    7.1,
+    7.1,
+    12.2,
+    13.8,
+    6.7,
+    8.5,
+    6.5,
+    6.1,
+    6.4,
+    6.5,
+    6.1,
+    7.2,
+    6.6,
+    7.4,
+    6.1,
+    6.8,
+    12.8,
+    11.1,
+    6.2,
+    6.4,
+    6.4,
+    6.1,
+    6.3,
+    8.7,
+    7.4,
+    9.4,
+    6.3,
+    7.9,
+    6.5,
+    6.4,
+    15.4,
+    9.4,
+    6.3,
+    47.4
+   ],
+   "ram_used": [
+    70353756160,
+    70321405952,
+    70284603392,
+    70262280192,
+    70387703808,
+    70314864640,
+    70312120320,
+    70299967488,
+    70299987968,
+    70294355968,
+    70301368320,
+    70293327872,
+    70290792448,
+    70280925184,
+    70300200960,
+    70377836544,
+    70448394240,
+    70448910336,
+    70574612480,
+    70739390464,
+    70512533504,
+    70533234688,
+    70513684480,
+    70496215040,
+    70484873216,
+    70469386240,
+    70452416512,
+    70445555712,
+    70424002560,
+    70434533376,
+    70424702976,
+    70408409088,
+    70395523072,
+    70388035584,
+    70353256448,
+    70333558784,
+    70326820864,
+    70357315584,
+    70361923584,
+    70355750912,
+    70357520384,
+    70490038272,
+    70530985984,
+    70524338176,
+    70524243968,
+    70525259776,
+    70528827392,
+    70526148608,
+    70526631936,
+    70541975552,
+    70541778944,
+    70536822784,
+    70537621504,
+    70537134080,
+    70534877184,
+    70532685824,
+    70529556480,
+    70530998272,
+    70534545408,
+    70762872832
+   ],
+   "disk_read_mb": [
+    0.0,
+    0.0,
+    71.3,
+    0.0,
+    0.0,
+    79.43,
+    0.0,
+    72.4,
+    4.53,
+    0.0,
+    54.62,
+    0.0,
+    42.73,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    3.32,
+    0.6,
+    0.01,
+    0.0,
+    0.01,
+    0.0,
+    0.0,
+    0.02,
+    0.0,
+    0.02,
+    0.0,
+    0.0,
+    0.03,
+    0.0,
+    0.03,
+    0.0,
+    0.0,
+    0.73,
+    0.0,
+    0.01,
+    0.0,
+    0.0,
+    0.01,
+    0.0,
+    0.02,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    12.58,
+    0.0,
+    0.0,
+    71.88,
+    0.0,
+    33.04,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.91
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    93.52,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    110.51
+   ]
+  },
+  "time": 1790718828.3451
+ }
+}

bench/results/2026-09-29-rtx3090-epyc-milan/data/native-v0.1.26-IQ3_S-2x3090-auto/speed-32k-3.json

@@ -0,0 +1,721 @@
+{
+ "label": "native-v0.1.26-IQ3_S-2x3090-auto",
+ "mode": "speed",
+ "ctx": "32k",
+ "target_tokens": 31488,
+ "run": 3,
+ "run_id": "4e71f26e7fd8",
+ "corpus_repeated": false,
+ "time": "2026-09-29T21:53:48",
+ "prompt_tokens": 31604,
+ "completion_tokens": 49,
+ "ttft_s": 42.269,
+ "e2e_s": 42.716,
+ "api_prompt_tps": 747.7,
+ "api_decode_tps": 107.5,
+ "engine_prompt_tps": 750.5,
+ "engine_decode_tps": 106.3,
+ "log_lines": [
+  "strata serve: prompt 31604 tokens = 0 reused + 31604 read in 42111 ms (750.5 tok/s), 49 generated in 461 ms (106.3 tok/s), drafts accepted 33 of 37, 2 checkpoints",
+  "strata serve: decode expert cache hit rate: 99.1% (26163 hits / 26396 lookups)"
+ ],
+ "answer_head": "I'll start by exploring the repository structure to understand what's there and identify the \"last file\" being referenced.",
+ "metrics_after": {
+  "engine": {
+   "model": "qwen3.8-flash-next-iq3_s",
+   "max_context": 32768,
+   "images": false,
+   "version": "0.1.26",
+   "context": 32768,
+   "kv": "int8",
+   "kv_resident": 0,
+   "expert_slots": 9376,
+   "expert_cache_mib": 17297,
+   "spec": 6,
+   "mtp_max": 4,
+   "lookup": 3,
+   "vram_free_mib": 635,
+   "cvec": 0,
+   "arena_mib": 47962,
+   "pool_workers": 19,
+   "pcie_frac": "0.55",
+   "spec_min_p": "0.50",
+   "engine": "0.1.26"
+  },
+  "live": {
+   "state": "idle",
+   "queued": 0,
+   "phase": null,
+   "prompt_tokens": null,
+   "prompt_read": null,
+   "prompt_total": null,
+   "generated": null,
+   "max_tokens": null,
+   "elapsed_s": null,
+   "tok_s": null,
+   "tok_s_mean": null,
+   "tok_s_window_s": null
+  },
+  "requests": [
+   {
+    "projection": null,
+    "time": 1790718828.4807332,
+    "duration_s": 42.6,
+    "finish": "stop",
+    "prompt_tokens": 31604,
+    "reused": 0,
+    "output_tokens": 49,
+    "engine_generated": 49,
+    "prompt_ms": 42110.8,
+    "decode_ms": 460.9,
+    "decode_tok_s": 106.3,
+    "hit_rate": 0.991
+   },
+   {
+    "projection": null,
+    "time": 1790718784.8375118,
+    "duration_s": 43.0,
+    "finish": "stop",
+    "prompt_tokens": 31633,
+    "reused": 0,
+    "output_tokens": 88,
+    "engine_generated": 88,
+    "prompt_ms": 42216.7,
+    "decode_ms": 776.7,
+    "decode_tok_s": 113.3,
+    "hit_rate": 0.978
+   },
+   {
+    "projection": null,
+    "time": 1790718743.8685048,
+    "duration_s": 40.3,
+    "finish": "stop",
+    "prompt_tokens": 28315,
+    "reused": 0,
+    "output_tokens": 84,
+    "engine_generated": 84,
+    "prompt_ms": 39286.5,
+    "decode_ms": 1011.1,
+    "decode_tok_s": 83.1,
+    "hit_rate": 0.949
+   }
+  ],
+  "requests_kept": 3,
+  "totals": {
+   "since": 1790718725.4039552,
+   "requests": 3,
+   "prompt_tokens": 91552,
+   "reused": 0,
+   "output_tokens": 221,
+   "prompt_ms": 123614.0,
+   "decode_ms": 2248.7000000000003
+  },
+  "hardware": {
+   "gpus": [
+    {
+     "index": 0,
+     "util": 39,
+     "mem_used": 25212944384,
+     "mem_total": 25769803776,
+     "temp": 47,
+     "power": 127.526
+    },
+    {
+     "index": 1,
+     "util": 2,
+     "mem_used": 24227282944,
+     "mem_total": 25769803776,
+     "temp": 50,
+     "power": 202.315
+    }
+   ],
+   "gpu_util": 20.5,
+   "gpu_mem_used": 49440227328,
+   "gpu_mem_total": 51539607552,
+   "gpu_temp": 50,
+   "gpu_power": 329.841,
+   "gpu_power_limit": 560.0,
+   "gpu_pcie_gen": 4,
+   "gpu_pcie_gen_max": 4,
+   "gpu_pcie_width": 16,
+   "gpu_pcie_rx_mb": 19.740234375,
+   "gpu_pcie_tx_mb": 54.21484375,
+   "cpu": 32.2,
+   "ram_used": 70312075264,
+   "ram_total": 177175990272,
+   "disk_read_mb": 0.0,
+   "disk_write_mb": 0.09328657441898458,
+   "tok_s": 97.74566314411967,
+   "tok_s_mean": 97.74268443960047
+  },
+  "hardware_static": {
+   "gpu_name": "NVIDIA GeForce RTX 3090 + NVIDIA GeForce RTX 3090",
+   "gpu_count": 2,
+   "cpu_name": "AMD EPYC 7453 28-Core Processor",
+   "cores": 20,
+   "threads": 20,
+   "psutil": true
+  },
+  "history": {
+   "gpu_util": [
+    25.5,
+    38.5,
+    31.5,
+    24.5,
+    30.0,
+    26.0,
+    31.5,
+    19.0,
+    86.5,
+    28.0,
+    22.5,
+    32.0,
+    26.0,
+    77.5,
+    22.5,
+    22.5,
+    34.0,
+    26.0,
+    20.5,
+    32.5,
+    0.0,
+    36.5,
+    37.0,
+    26.0,
+    32.0,
+    37.0,
+    24.0,
+    32.5,
+    20.5,
+    29.0,
+    25.0,
+    27.5,
+    30.5,
+    24.0,
+    35.0,
+    28.5,
+    29.0,
+    30.0,
+    29.5,
+    33.5,
+    44.5,
+    55.5,
+    36.0,
+    25.0,
+    33.5,
+    47.0,
+    15.5,
+    32.5,
+    24.0,
+    32.5,
+    29.0,
+    55.0,
+    34.0,
+    48.0,
+    33.0,
+    22.5,
+    31.5,
+    24.5,
+    20.0,
+    20.5
+   ],
+   "gpu_mem_used": [
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328,
+    49440227328
+   ],
+   "gpu_temp": [
+    51,
+    50,
+    49,
+    50,
+    49,
+    51,
+    49,
+    50,
+    51,
+    49,
+    50,
+    50,
+    51,
+    52,
+    50,
+    50,
+    50,
+    51,
+    52,
+    50,
+    49,
+    49,
+    49,
+    51,
+    50,
+    50,
+    50,
+    50,
+    51,
+    50,
+    50,
+    51,
+    50,
+    51,
+    50,
+    51,
+    51,
+    50,
+    52,
+    50,
+    51,
+    50,
+    50,
+    51,
+    50,
+    51,
+    51,
+    51,
+    51,
+    51,
+    51,
+    51,
+    50,
+    52,
+    52,
+    52,
+    51,
+    52,
+    52,
+    50
+   ],
+   "gpu_power": [
+    385.57,
+    368.88,
+    396.03,
+    374.4,
+    393.23,
+    385.24,
+    406.68,
+    391.86,
+    364.28,
+    409.58,
+    388.38,
+    389.1,
+    390.65,
+    372.81,
+    415.25,
+    390.44,
+    384.85,
+    382.05,
+    377.98,
+    330.14,
+    415.76,
+    348.22,
+    407.06,
+    354.03,
+    392.05,
+    392.72,
+    370.96,
+    399.97,
+    402.84,
+    387.68,
+    394.33,
+    359.55,
+    419.05,
+    403.04,
+    384.68,
+    390.64,
+    393.93,
+    389.6,
+    362.93,
+    373.48,
+    405.22,
+    378.6,
+    399.07,
+    380.19,
+    386.69,
+    409.76,
+    359.41,
+    400.68,
+    368.54,
+    396.07,
+    393.99,
+    371.52,
+    407.92,
+    367.65,
+    416.33,
+    386.19,
+    394.79,
+    409.75,
+    373.56,
+    329.84
+   ],
+   "gpu_pcie_rx_mb": [
+    6062.41,
+    5581.95,
+    5691.53,
+    8234.83,
+    8344.89,
+    7880.73,
+    6094.07,
+    8294.58,
+    5858.85,
+    5465.17,
+    6922.82,
+    4432.29,
+    6296.59,
+    5837.44,
+    7103.97,
+    7604.84,
+    4756.35,
+    4899.02,
+    5517.96,
+    50.97,
+    0.67,
+    11557.34,
+    5125.33,
+    6536.1,
+    6042.86,
+    7341.43,
+    5299.47,
+    6137.51,
+    6431.72,
+    5859.47,
+    4887.1,
+    5919.46,
+    5763.62,
+    94.17,
+    6438.59,
+    7535.84,
+    6171.89,
+    7355.36,
+    4306.32,
+    5857.37,
+    4681.59,
+    5568.03,
+    5823.33,
+    5368.61,
+    7806.78,
+    7675.93,
+    8469.58,
+    5669.88,
+    14723.06,
+    5790.85,
+    6188.01,
+    6980.23,
+    7332.23,
+    12898.87,
+    6754.21,
+    6340.74,
+    6000.61,
+    6420.09,
+    4455.66,
+    19.74
+   ],
+   "cpu": [
+    6.1,
+    6.8,
+    12.8,
+    11.1,
+    6.2,
+    6.4,
+    6.4,
+    6.1,
+    6.3,
+    8.7,
+    7.4,
+    9.4,
+    6.3,
+    7.9,
+    6.5,
+    6.4,
+    15.4,
+    9.4,
+    6.3,
+    47.4,
+    36.1,
+    6.3,
+    6.7,
+    6.6,
+    5.7,
+    7.4,
+    6.2,
+    7.4,
+    6.0,
+    6.6,
+    15.5,
+    14.6,
+    5.8,
+    6.4,
+    6.5,
+    6.2,
+    11.6,
+    8.8,
+    7.8,
+    6.2,
+    6.9,
+    6.0,
+    5.5,
+    7.3,
+    17.5,
+    8.0,
+    7.9,
+    6.6,
+    6.2,
+    6.2,
+    6.1,
+    6.6,
+    5.7,
+    6.8,
+    7.1,
+    7.8,
+    6.2,
+    9.8,
+    15.0,
+    32.2
+   ],
+   "ram_used": [
+    70357520384,
+    70490038272,
+    70530985984,
+    70524338176,
+    70524243968,
+    70525259776,
+    70528827392,
+    70526148608,
+    70526631936,
+    70541975552,
+    70541778944,
+    70536822784,
+    70537621504,
+    70537134080,
+    70534877184,
+    70532685824,
+    70529556480,
+    70530998272,
+    70534545408,
+    70762872832,
+    70460293120,
+    70452703232,
+    70444961792,
+    70428729344,
+    70420193280,
+    70418821120,
+    70406471680,
+    70396342272,
+    70389112832,
+    70380965888,
+    70312722432,
+    70348423168,
+    70338981888,
+    70328791040,
+    70326034432,
+    70312820736,
+    70085947392,
+    69987848192,
+    70072119296,
+    70060589056,
+    70056861696,
+    70179471360,
+    70176550912,
+    70159552512,
+    70270476288,
+    70270668800,
+    70271184896,
+    70263926784,
+    70264184832,
+    70264291328,
+    70265167872,
+    70267035648,
+    70267035648,
+    70264389632,
+    70261067776,
+    70265782272,
+    70268100608,
+    70275043328,
+    70091866112,
+    70312075264
+   ],
+   "disk_read_mb": [
+    0.0,
+    0.01,
+    0.0,
+    0.02,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    12.58,
+    0.0,
+    0.0,
+    71.88,
+    0.0,
+    33.04,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.91,
+    0.83,
+    0.04,
+    0.0,
+    0.0,
+    0.01,
+    0.0,
+    0.03,
+    0.0,
+    0.0,
+    0.03,
+    0.0,
+    0.05,
+    0.0,
+    0.0,
+    0.04,
+    0.0,
+    0.04,
+    0.0,
+    0.04,
+    0.0,
+    0.0,
+    0.04,
+    0.0,
+    0.0,
+    0.04,
+    0.0,
+    0.01,
+    0.0,
+    0.02,
+    0.0,
+    0.0,
+    0.01,
+    0.0,
+    0.22,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+   ],
+   "tok_s": [
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    110.51,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    97.75
+   ]
+  },
+  "time": 1790718871.5639336
+ }
+}