Release notes 0.2.7: update, tray and speed lines confirmed on the release packages; Strix Halo guide names the prompt used for the 4K row

docs/STRIX_HALO_WINDOWS.md

@@ -34,15 +34,15 @@ the default 8K context, the others 64K context with `--context 64k`):
 | Test | Result |
 | --- | --- |
 | Short chat, answer speed | **12.1 to 13.6 tok/s** |
-| 4K prompt | **214 to 226 tok/s** (about 19 s to the first token) |
+| 4K prompt | **214 to 234 tok/s** (about 18 s to the first token) |
 | 16K prompt | **326 tok/s** (51 s) |
 | 32K prompt | **342 tok/s** (97 s) |
 | Coding-agent session, 6 turns | 70% from the conversation cache; answers 14.2 tok/s; 17 to 31 s to the first token per turn |
 
-These are speed measurements. They say nothing about answer quality, and the short-chat range depends on the text. The DeepSeek 2.25 bpw set
+The prompt rows use the word-list prompt of `tools/strata_bench.py`; ordinary text is costlier for the experts and reads slower (124 to 164 tok/s on 3 to 5K-token pieces of prose). Measured again on the final build, the 4K row reads 229 to 234 tok/s warm. These are speed measurements. They say nothing about answer quality, and the short-chat range depends on the text. The DeepSeek 2.25 bpw set
 and the other Qwen sizes were not measured for this page.
 
-The DeepSeek 4K prompt here (214 to 226 tok/s) is higher than the 87 tok/s on [STRIX_HALO.md](STRIX_HALO.md), which was measured on 2026-10-25 with an
+The DeepSeek 4K prompt here (214 to 234 tok/s) is higher than the 87 tok/s on [STRIX_HALO.md](STRIX_HALO.md), which was measured on 2026-10-25 with an
 earlier build. The 0.2.7 DeepSeek defaults explain most of the gap (the same build with `DS4_DEFAULTS=026` reads 133 to 139 tok/s); the table there
 changes one thing at a time.
 

docs/release-notes-0.2.7.md

@@ -2,8 +2,6 @@
 
 The app and the Terminal are 0.2.7. Control and every engine package (Qwen and DeepSeek) are 0.1.52, because both engines changed.
 
-DRAFT of 27 October. Text in square brackets that starts with "pending" or "TO CONFIRM" is work that was not merged or checked when this was written. `phaseA-tests\rel027\check_notes027.py` lists them and removes the ones that landed. None of them may be left in the published text.
-
 ## What you will notice
 
 - **NVIDIA cards with 12 GB or less answer faster.** The router now prefers experts that are already on the card, which saves page-ins from RAM. On an RTX 3060 12 GB (Qwen3.8-Flash-Next IQ3_XXS, five paired runs against the same build with the setting off), a story answer went from 46.2 to 53.1 tok/s (+15%) and a code answer from 45.7 to 62.5 tok/s (+37%). It picks a slightly different set of experts, so the wording of answers changes. We checked the answers on that card (IQ3_XXS) with 80 tasks and saw no copy or code errors. Agent loops may finish slightly less often, within the run-to-run spread: out of 10 agent tasks, 4.5 passed on average over 4 runs at 1.5, against 5.6 over 7 runs with the setting off, where the off runs alone ranged from 4 to 6. A stronger setting (2.0) did show copy and code defects, so the default is 1.5. It applies to a discrete NVIDIA card of 13 GiB or less; larger cards, Radeon and Strix Halo are not changed. Off: the row "Faster answers on 12 GB NVIDIA cards" in the Expert settings (Models, Native engine settings, Speed), or `STRATA_ROUTE_PRIOR=0`.
@@ -15,8 +13,8 @@ DRAFT of 27 October. Text in square brackets that starts with "pending" or "TO C
   | 32K | 2,491 tok/s | 2,802 tok/s (+12%) | 64.9 tok/s | 85.1 tok/s (+31%) |
 
   Answers can differ in wording because the work is split differently; 30 test tasks passed in every arm with no invented fact. Off: "Faster answers on Radeon RX 9000 / AI PRO R9700".
-- **DeepSeek-V4.1-Flash runs on Ryzen AI Max (Strix Halo) PCs with Windows.** It has its own engine package for the gfx1151 chip, and the app or `strata launch` downloads it with the model. The new guide [docs/STRIX_HALO_WINDOWS.md](STRIX_HALO_WINDOWS.md) has the numbers and the traps, measured on a GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB shared memory, Adrenalin 26.10.1). DeepSeek 2.00 answers a short chat at 12 to 14 tok/s and reads a 4K prompt at 214 to 226 tok/s, a 16K prompt at 326 and a 32K prompt at 342 tok/s. Qwen IQ3_S on the same PC: chat 44 tok/s, 4K prompt 755, 32K prompt 792 tok/s. [TO CONFIRM: re-measure the DeepSeek and Qwen rows on the final build if strix is lent before the release] The shared-expert stream is off by default on Windows there, because it is slower: 43.6 to 46.6 tok/s decode (+6.9%, three paired starts), same token ids. Only the 128 GB machine was tested. You need Adrenalin 26.10.1 or newer.
-- **DeepSeek reads prompts faster on most PCs.** The engine no longer re-reads a batch of experts from the SSD after every prompt, picks the attention buffer size by itself and fills the RAM store more cleverly. On an RTX 5070 (12 GB, 64 GB RAM, 2.25 set, three paired runs against an earlier 0.2.7 candidate): 4K prompt 116 to 170 tok/s (+47%), 8K prompt 202 to 268 tok/s (+33%). On one R9700 with the 2.25 set: 32K prompt 382 to 444 tok/s (+16%), 8K prompt 200 to 286 tok/s (+43%, but that prompt is limited by SSD reads and varies a lot between runs). The cost: the first words after a long prompt can come slower, because the store is no longer pre-filled. On the RTX 5070 a long answer still finished 8.7% sooner overall (137.5 s against 150.6 s); on one R9700 a 300-token answer after an 8K prompt took 51.9 s without the pre-fill and 48.6 s with it. `DS4_SETTLE_STORE=1` brings the pre-fill back. The speed-up switch "DeepSeek speed-ups" turns the new behaviour off in one step.
+- **DeepSeek-V4.1-Flash runs on Ryzen AI Max (Strix Halo) PCs with Windows.** It has its own engine package for the gfx1151 chip, and the app or `strata launch` downloads it with the model. The new guide [docs/STRIX_HALO_WINDOWS.md](STRIX_HALO_WINDOWS.md) has the numbers and the traps, measured on a GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB shared memory, Adrenalin 26.10.1). DeepSeek 2.00 answers a short chat at 12 to 14 tok/s and reads a 4K prompt at 214 to 234 tok/s, a 16K prompt at 326 and a 32K prompt at 342 tok/s. Those prompt rows use the word-list prompt of `tools/strata_bench.py`; ordinary prose is slower (124 to 164 tok/s on 3 to 5K-token pieces). Qwen IQ3_S on the same PC: chat 44 to 51 tok/s, 4K prompt 755, 32K prompt 792 tok/s. We measured both again on the final release package (the 4K DeepSeek prompt 229 to 234 tok/s warm, 186 to 225 on the first cold run; the Qwen prompt rows within 1%). The shared-expert stream is off by default on Windows there, because it is slower: 43.6 to 46.6 tok/s decode (+6.9%, three paired starts), same token ids. Only the 128 GB machine was tested. You need Adrenalin 26.10.1 or newer.
+- **DeepSeek reads prompts faster on most PCs.** The engine no longer re-reads a batch of experts from the SSD after every prompt, picks the attention buffer size by itself and changes how the RAM store is filled. On an RTX 5070 (12 GB, 64 GB RAM, 2.25 set, three paired runs against an earlier 0.2.7 candidate): 4K prompt 116 to 170 tok/s (+47%), 8K prompt 202 to 268 tok/s (+33%). On one R9700 with the 2.25 set: 32K prompt 382 to 444 tok/s (+16%), 8K prompt 200 to 286 tok/s (+43%, but that prompt is limited by SSD reads and varies a lot between runs). The first words after a long prompt can come slower, because the store is no longer pre-filled. On the RTX 5070 a long answer still finished 8.7% sooner overall (137.5 s against 150.6 s); on one R9700 a 300-token answer after an 8K prompt took 51.9 s without the pre-fill and 48.6 s with it. `DS4_SETTLE_STORE=1` brings the pre-fill back. The speed-up switch "DeepSeek speed-ups" turns the new behaviour off in one step.
 - **Four Radeon AI PRO R9700 cards run DeepSeek faster, with five experts per word by default.** With the launcher's own settings, DeepSeek 2.25: an 8K prompt 342 to 399 tok/s on the first read and 967 to 1,350 once warm (+17%, +40%), a 32K prompt 1,127 to 1,604 first and 1,183 to 1,697 warm (+42%, +43%), decode on code 88.9 to 95.0 tok/s (+7%) and on an agent task 73.5 to 79.7 (+8%). Loading takes 58 to 60 s instead of 51 s. The default is now "Faster" (5 of 6 experts per word); the quality run passed 19 of 19 tasks against 18 of 19 with six experts, and the distance to the reference model is the same (0.1102 against 0.1102). Choose Full quality in the app, or `--experts 6`, to use six.
 - **DeepSeek can use 512K and 1M contexts.** Setup, the Terminal and the app offer them up to the limit of the model files, with a plain "not tested yet" note past 256K. The default stays 8K, and the app now loads a DeepSeek model with the context you chose. On an RTX 5070 a 1M context loaded in 18 s and cost about 1 GB of graphics memory, which pushed 136 experts off the card. We did not test long prompts at these sizes. The idea comes from Project Maya v1.1.28 (#442, by @needmorevram).
 - **Two NVIDIA cards read long prompts much sooner on a layer split.** On a layer split over two CUDA cards the prompt is now read layer by layer in large pieces (layer-major prefill, on by default), so each layer's experts are read once per piece instead of once per 8,192 tokens. On two RTX A4000 (16 GB each, Qwen IQ3_XXS with most experts streamed from RAM, five paired runs): the first word after a 32K prompt came after 27.7 s instead of 141.8 s, after a 20K prompt after 17.5 s instead of 98.8 s, after an 8K prompt after 15.2 s instead of 41.8 s. Decode speed is the same (38.6 against 38.4 tok/s). Quality: 12 of 12 needles found with both, the quick suite passed 18 of 19 tasks in all three arms, and the first-token probabilities moved by 0.0007 to 0.009 (KL; the same top choice in every check), so wording can differ a little. If a card has no room for the bigger step, the engine reads the old way. From PR #3976 by @Norhiro, building on @vizdatom's #1670. One card, Radeon and the approximate-read mode keep the old path. Off: `STRATA_PREFILL_LAYER_MAJOR=0`; `STRATA_DEFAULTS=026` gives the old path.
@@ -24,7 +22,7 @@ DRAFT of 27 October. Text in square brackets that starts with "pending" or "TO C
 - **DeepSeek reads pictures by default.** Setup and `strata launch` start DeepSeek-V4.1-Flash with the engine's own vision tower (319 MiB, no separate reader). It costs a one-time download of about 1 GB (the tower's weights, 972 MB, checked against a pinned hash) and about 1.3 GB more RAM on four R9700 (0.2 GB on one card); the graphics memory is taken from the expert cache, so the total does not grow. On four R9700 a picture question (left half red, right half blue) was answered correctly, 7.8 s for the first picture and 0.2 s once warm; on one R9700 12.7 s and 0.5 s; text requests after pictures work. The text-only answers on the agent prompt are identical with and without it; the distance to the reference model moved by +0.0014 on four R9700 and by -0.003 on one (gate 0.006). Not wanted: `--vision off` on launch, or `--vision no` in setup, leaves the tower out. Checked on Linux (R9700, boston); not on Windows or Strix Halo.
 - **More cards get small gains from kernel changes that were measured.** On an RTX PRO 5000 (72 GB, Qwen IQ3_S, five paired runs): story answers 195.9 to 211.8 tok/s (+8.1%), code 240.6 to 244.7 (+1.7%), prompts +1.2% at 4K, +1.5% at 8K, +1.6% at 16K. On two RTX A4000: story +2.2%, code +0.5%. These switches sum numbers in another order, so a reply can differ from 0.2.6 at a near-tie. RTX 40 cards (compute capability 8.9) use measured speed tables for the quantised matrix products; they are bit for bit the same as before and we have no Ada card, so the reporter's measurements are the only ones. Off: `STRATA_MMVQ_IL_89=0`. A100-class cards (sm_80) get the bitwise-identical defaults of #3779 (wider dequantisation, tuned tables, measured only on a CMP 170HX by the contributor); its many opt-ins stay off, and the reporters are asked to test. Off: `STRATA_DEQUANT_WIDE=0`, `STRATA_MMVQ_IL_SM80=0`.
 - **The served web chat page gets a large update.** Wide windows use the width and narrow screens fit (#3176). Saved chats with search, rename and delete, editing a question, rewinding to an earlier turn and branching a new chat from it, sending a message while the answer is still coming (wait, send after, or interrupt), math written in LaTeX rendered with KaTeX, a sandboxed preview of HTML and SVG the model writes, and Load and Unload buttons in the header. The chat view is translated into the same languages as the app, French included. The history features are off until you switch them on in Chat settings: with them off the page sends the same requests as before. Monitor, Images and About are still English.
-- **The desktop app.** French is the ninth language. Settings now has: a sound when a task finishes (on request), a desktop notification when Manual mode needs your approval, minimise to the system tray, a fixed port so API clients keep working across updates (with a warning when the port is busy), and an interface size up to 200%. The Monitor has a readings strip: power draw, an electricity price you set (in your local currency, found from the system region), disk temperature where Windows or Linux can report it. The DeepSeek card says how much free disk the set needs. Not tried inside the real packaged app on screen yet: tray icon, the native notification and the busy-port warning. [TO CONFIRM: run once in the release e2e]
+- **The desktop app.** French is the ninth language. Settings now has: a sound when a task finishes (on request), a desktop notification when Manual mode needs your approval, minimise to the system tray, a fixed port so API clients keep working across updates (with a warning when the port is busy), and an interface size up to 200%. The Monitor has a readings strip: power draw, an electricity price you set (in your local currency, found from the system region), disk temperature where Windows or Linux can report it. The DeepSeek card says how much free disk the set needs. Checked in the packaged app on a PC without a screen session: with the port taken, the app starts on the next free port and reports it, and the shell accepts a notification. The tray icon, the pop-up itself and the warning as drawn in the window were not seen on screen.
 - **Speed switches.** In Models, Native engine settings, Speed (and in the Terminal's Advanced table): "Faster long prompts" (off by default), "Faster answers on 12 GB NVIDIA cards", "Faster answers on Radeon RX 9000 / AI PRO R9700", "DeepSeek speed-ups". The Terminal also has "Qwen: 0.2.6 behaviour" for troubleshooting.
 
 ## Going back to 0.2.6
@@ -46,13 +44,11 @@ A variable or flag you set yourself still wins over the switch, and the older si
 
 ## Fixed, from your reports
 
-Each issue number gets its own reply.
-
 - Chat: scrolling up while an answer streams works (#4014); a request that timed out shows a badge (#3991).
 - The Monitor asks the NVIDIA tool only while it is open or a model runs, which stops the Windows stutter (#4066). The app no longer insists on CUDA when you have a HIP card on Windows (#3892), and the source-checkout host starts an engine with an empty API key (#3851). Deleting a model in the app removes all files of a multi-file model and leaves your own files (#3716).
 - The Terminal: `strata launch --set dspark=on` works (#3959); `launch --show-key` knows the config setup wrote (#3570); a model on disk in a differently cased folder is found on Linux instead of being offered for download again (#3996); `--spec 5` can be saved with a warning (#3844).
 - Manual mode: read-only commands that have write or execute options now ask first (#3975).
-- Engine: a conversation cache no longer reuses another conversation's keys and values (#1503); a short draft-vocabulary row can't be written past (#3911); a checkpoint save that runs out of memory no longer exits the engine (#3350); one cause of the free memory of the second card shrinking with every long cold prompt on a layer split is fixed, a leaked copy stream (#3470, #3350); a hand build for RTX 50 no longer ends up as sm_75 (#4029, #4023); the DeepSeek CUDA packages now include RTX 40 cards (sm_89, #3935); an undeclared tool call returned as text is recovered, declared-only kept (#3796); `--spec 5` and other values outside the tuner's range can be saved with a warning (#3844).
+- Engine: a conversation cache no longer reuses another conversation's keys and values (#1503); a short draft-vocabulary row can't be written past (#3911); a checkpoint save that runs out of memory no longer exits the engine (#3350); one cause of the free memory of the second card shrinking with every long cold prompt on a layer split is fixed, a leaked copy stream (#3470, #3350); a hand build for RTX 50 no longer ends up as sm_75 (#4029, #4023); the DeepSeek CUDA packages now include RTX 40 cards (sm_89, #3935); an undeclared tool call returned as text is recovered, declared-only kept (#3796).
 - Engine, found by reading the code and the pull requests: a failed read in the per-layer table reader no longer leaves the next request waiting for ever (#3602; the reporter's NaN did not reproduce here, `STRATA_PLE_CHECK=1` re-reads a suspect row and prints it); a conversation restore that would have to create a new copy stream on a card with almost no free memory goes back to the cache instead of failing (#2409); an engine that cannot allocate on a layer split says how much memory it planned to keep free and how much is free (#3638, #3702); the fused int8 tails of `STRATA_QFUSE` used a division that differed from the matrix kernels in about one code per million (#3948, found by a parity test, that switch is off by default, the default path is unchanged); `/v1/responses` accepts -1 and 0 as output limits and reports timings (#4036, #3291); logprobs and allowed token ids on /v1/chat/completions (#3200, partly).
 - Opt-in switches from pull requests, each checked for exactness or by unit tests and builds, not for speed on your card: a bigger Pascal (GP100) set (`STRATA_DOWN_WS=1`, `STRATA_MTP_Q8_SM60=1`, `STRATA_MMQ_WS=1`, `STRATA_PATTN_SM60=1`, `STRATA_EXPERT_NIBBLE=1`), `STRATA_PF_FUSED_Q2N=1` for the Q2_0 pack on sm_80 and newer, `STRATA_SELECT_LONG=1` for decoding past 64K cells, `STRATA_VRAM_FREE=device` (Windows, NVML), `STRATA_RAM_ADAPT`, `STRATA_PIPE_ADAPT_EVERY`, `STRATA_SPEC_PROB=1` (a gated draft proposal that keeps the target probabilities, #3416), the sparse copy events on Windows HIP (#4005), and an ARM64 Linux port of the CPU engine whose x86 code compiles to the same objects (#3622, built and cross-compiled, never run on an ARM machine). The speed figures in those pull requests are their authors', not ours.
 - Setup: ISTA re-published the first shard of every DeepSeek set on 26 October with a larger chat template; setup refused a copy of it from `--model-path` with "cut short or another version". It accepts it now (by its own size and hash; downloads stay on the pinned revision). The same 0.2.6 setup bug is fixed for people who already have the files.
@@ -77,13 +73,13 @@ Names stay on the commits: 55 contributors' pull requests were ported with their
 
 ## Updating
 
-- **App:** the in-app updater installs the new installer. The app then offers the 0.1.52 engine. [TO CONFIRM with the update test]
-- **Terminal:** run `strata update`. It fetches Control 0.1.52 and the newer engine. [TO CONFIRM with the update test]
+- **App:** the in-app updater installs the new installer. The app then offers the 0.1.52 engine.
+- **Terminal:** run `strata update`. It fetches Control 0.1.52 and the newer engine in the same run, and keeps the old engine so `strata components rollback` can return to it.
 - **DeepSeek engine:** updates itself on the next `strata launch`.
 
 ## Downloads
 
-Three installers, the three Control packages (0.1.52), 13 Qwen engine packages and 4 DeepSeek engine packages (all 0.1.52: Windows CUDA 13, Windows AMD for Ryzen AI Max, Linux CUDA 13, Linux AMD rx9070), plus `strata-feed.json` with its signature, `latest.json`, `install-manifest.txt`, `install.sh`, `install.ps1` and `SHA256SUMS.txt`. The DeepSeek CUDA packages are built for sm_86, sm_89 and sm_120.
+Three installers (Windows, Linux AppImage, Mac dmg) and the Mac updater archive `Strata.app.tar.gz`, the three Control packages (0.1.52), 13 Qwen engine packages and 4 DeepSeek engine packages (all 0.1.52: Windows CUDA 13, Windows AMD for Ryzen AI Max, Linux CUDA 13, Linux AMD rx9070), plus `strata-feed.json` with its signature, `latest.json`, `install-manifest.txt`, `install.sh`, `install.ps1` and `SHA256SUMS.txt`. The DeepSeek CUDA packages are built for sm_86, sm_89 and sm_120.
 
 ---