Niko1221/Strata
1
0 Fork 0
mirror of https://github.com/Niko1221/Strata.git synced 2026-11-07 14:21:06 -10:00
Code Issues Packages Projects Releases 1 Wiki Activity

Engine 0.1.30: short prompts up to 28% faster (every expert streams from 1024-token chunks), the resident low-RAM variant, the multi-GPU session carve (#216), AMD RDNA4, idle unload (#208); opt-ins: rope scaling (#84), conversation cache (#189), STRATA_IQ_MT_MIN=1 (#152); setup requires it

Browse Source 
Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_0154bwiad8gY7wRehCXy27pN
This commit is contained in:
Niko1221andClaude Opus 5.5 committed 2026-09-30 19:34:50 +02:00
1 parent fb73292e03
commit 30ec18ec70
1 file changed
+1 -1
Download Patch File Download Diff File Expand all files Collapse all files
setup.py
+1 -1
View File
@@ -61,7 +61,7 @@ PREBUILT_ASSET = "strata-windows-x64.zip" if WIN else "strata-linux-x64.zip"
# the CUDA libraries the ready-made engine loads (the same CUDA 13.0 it is built with), from NVIDIA's pip packages
CUDA_WHEELS = ["nvidia-cublas==13.0.2.14", "nvidia-cuda-runtime==13.0.96"]
MIN_DRIVER = 580 # CUDA 13.0
MIN_ENGINE = (0, 1, 29) # v0.1.29: sampled answers faster (split top-k), #154 correctness fixes; v0.1.28: the expert cache reserves the draft head, a cancelled request no longer fails the next; v0.1.27: RTX 20 (sm_75) in the ready-made engine, the HIP build without CUDA headers; v0.1.26: the draft layer's prompt pass in batches; v0.1.25: faster prompts (grouping off the copy engine, fused hyper-connection kernels), AMD HIP backend, --kv k8v4; v0.1.24: long prompts faster (QSA select on tensor cores); v0.1.23: image requests honor sampling, 8 GB cards start, batched verify window; v0.1.22: faster prompts (tensor-core attention), multi-GPU across images/steering/KV streaming; v0.1.21: multi-GPU layer split (--gpus); v0.1.20: system-prompt checkpoint, PCIe probe, hit rate; v0.1.19: penalties
MIN_ENGINE = (0, 1, 30) # v0.1.30: short prompts faster (streaming from 1024 tokens), resident low-RAM variant, multi-GPU session carve, RDNA4; v0.1.29: sampled answers faster (split top-k), #154 correctness fixes; v0.1.28: the expert cache reserves the draft head, a cancelled request no longer fails the next; v0.1.27: RTX 20 (sm_75) in the ready-made engine, the HIP build without CUDA headers; v0.1.26: the draft layer's prompt pass in batches; v0.1.25: faster prompts (grouping off the copy engine, fused hyper-connection kernels), AMD HIP backend, --kv k8v4; v0.1.24: long prompts faster (QSA select on tensor cores); v0.1.23: image requests honor sampling, 8 GB cards start, batched verify window; v0.1.22: faster prompts (tensor-core attention), multi-GPU across images/steering/KV streaming; v0.1.21: multi-GPU layer split (--gpus); v0.1.20: system-prompt checkpoint, PCIe probe, hit rate; v0.1.19: penalties
PY_PACKAGES = ["numpy", "jinja2", "regex", "pyyaml", "tqdm", "requests", "cmake", "ninja", "pillow", "psutil"]
MODELS = {