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 13, 22:00 UTC
[XPU]Refine Dockerfile.xpu, avoid oneccl dependency issue (#27964)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Kunshang Ji committed
Nov 3, 2025 at 15:36 UTC
7f4bdadb926936a11a88a619f56634061e824798
1 file changed
+4
-4
docker/Dockerfile.xpu
+4
-4
@@ -54,7 +54,7 @@ ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
54
55
RUN --mount=type=cache,target=/root/.cache/pip \
56
--mount=type=bind,source=.git,target=.git \
57
- python3 setup.py install
57
+ pip install --no-build-isolation .
58
59
CMD ["/bin/bash"]
60
@@ -64,9 +64,6 @@ FROM vllm-base AS vllm-openai
64
RUN --mount=type=cache,target=/root/.cache/pip \
65
pip install accelerate hf_transfer pytest pytest_asyncio lm_eval[api] modelscope
66
67
-RUN --mount=type=cache,target=/root/.cache/pip \
68
- pip uninstall oneccl oneccl-devel -y
69
-
67
# install development dependencies (for testing)
68
RUN python3 -m pip install -e tests/vllm_test_utils
69
@@ -74,4 +71,7 @@ RUN python3 -m pip install -e tests/vllm_test_utils
71
RUN python3 /workspace/vllm/tools/install_nixl_from_source_ubuntu.py
72
ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/python3.12/dist-packages/.nixl.mesonpy.libs/plugins/"
73
74
+RUN --mount=type=cache,target=/root/.cache/pip \
75
+ pip uninstall oneccl oneccl-devel -y
76
+
77
ENTRYPOINT ["vllm", "serve"]