biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Quantization] Bump to use latest bitsandbytes (#20424)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li
2025-07-03 21:58:46 +08:00
committed by GitHub
parent 7f0367109e
commit 1819fbda63
8 changed files with 14 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docker/Dockerfile
View File

@@ -498,7 +498,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.42.0' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
else \
uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.45.3' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.46.1' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
fi
ENV VLLM_USAGE_SOURCE production-docker-image