A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 01:00 UTC
[CI] Cleanup modelscope version constraint in Dockerfile (#21243)
Signed-off-by: Kay Yan <kay.yan@daocloud.io>
Kay Yan committed
Jul 21, 2025 at 11:13 UTC
8188196a1c8af26134d8e366ebe564c18fb95379
2 files changed
+2
-2
docker/Dockerfile
+1
-1
@@ -510,7 +510,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
510
else \
511
BITSANDBYTES_VERSION="0.46.1"; \
512
fi; \
513
- uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' "bitsandbytes>=${BITSANDBYTES_VERSION}" 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]
513
+ uv pip install --system accelerate hf_transfer modelscope "bitsandbytes>=${BITSANDBYTES_VERSION}" 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]
514
515
ENV VLLM_USAGE_SOURCE production-docker-image
516
docker/Dockerfile.xpu
+1
-1
@@ -47,7 +47,7 @@ FROM vllm-base AS vllm-openai
47
48
# install additional dependencies for openai api server
49
RUN --mount=type=cache,target=/root/.cache/pip \
50
- pip install accelerate hf_transfer pytest 'modelscope!=1.15.0'
50
+ pip install accelerate hf_transfer pytest modelscope
51
52
ENV VLLM_USAGE_SOURCE production-docker-image \
53
TRITON_XPU_PROFILE 1