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

[XPU]Replace pip in docker.xpu with uv pip (#31112)

Browse Source 
Signed-off-by: sihao.li <sihao.li@intel.com>
This commit is contained in:
sihao_li
2026-02-06 14:02:33 +08:00
committed by GitHub
parent 7439e4f41b
commit 6550815c3a
1 changed files with 44 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

70
docker/Dockerfile.xpu
View File

@@ -1,5 +1,10 @@
FROM intel/deep-learning-essentials:2025.3.2-0-devel-ubuntu24.04 AS vllm-base
WORKDIR /workspace/
ARG PYTHON_VERSION=3.12
ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/xpu"
RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null && \
echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list && \
add-apt-repository -y ppa:kobuk-team/intel-graphics
@@ -22,13 +27,16 @@ RUN apt clean && apt-get update -y && \
python3.12-dev \
python3-pip
RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.12 1
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.12 1
RUN apt update && apt upgrade -y && \
apt install -y libze1 libze-dev libze-intel-gpu1 intel-opencl-icd libze-intel-gpu-raytracing intel-ocloc && \
apt install -y intel-oneapi-compiler-dpcpp-cpp-2025.3
ENV PATH="/root/.local/bin:$PATH"
ENV VIRTUAL_ENV="/opt/venv"
ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
RUN curl -LsSf https://astral.sh/uv/install.sh | sh
RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
ENV PATH="$VIRTUAL_ENV/bin:$PATH"
# This oneccl contains the BMG support which is not the case for default version of oneapi 2025.2.
ARG ONECCL_INSTALLER="intel-oneccl-2021.15.7.8_offline.sh"
@@ -44,20 +52,31 @@ SHELL ["bash", "-c"]
CMD ["bash", "-c", "source /root/.bashrc && exec bash"]
WORKDIR /workspace/vllm
COPY requirements/xpu.txt /workspace/vllm/requirements/xpu.txt
COPY requirements/common.txt /workspace/vllm/requirements/common.txt
# suppress the python externally managed environment error
RUN python3 -m pip config set global.break-system-packages true
ENV UV_HTTP_TIMEOUT=500
RUN --mount=type=cache,target=/root/.cache/pip \
pip install --no-cache-dir \
-r requirements/xpu.txt
# Configure package index for XPU
ENV PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
ENV UV_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
ENV UV_INDEX_STRATEGY="unsafe-best-match"
ENV UV_LINK_MODE="copy"
# arctic-inference is built from source which needs torch-xpu properly installed
# used for suffix method speculative decoding
RUN --mount=type=cache,target=/root/.cache/pip \
pip install --no-cache-dir arctic-inference==0.1.1
RUN --mount=type=cache,target=/root/.cache/uv \
--mount=type=bind,src=requirements/common.txt,target=/workspace/vllm/requirements/common.txt \
--mount=type=bind,src=requirements/xpu.txt,target=/workspace/vllm/requirements/xpu.txt \
uv pip install --upgrade pip && \
uv pip install -r requirements/xpu.txt
# used for suffix method speculative decoding
# build deps for proto + nanobind-based extensions to set up the build environment
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install grpcio-tools protobuf nanobind
# arctic-inference is built from source which needs torch-xpu properly installed first
RUN --mount=type=cache,target=/root/.cache/uv \
source /opt/intel/oneapi/setvars.sh --force && \
source /opt/intel/oneapi/ccl/2021.15/env/vars.sh --force && \
export CMAKE_PREFIX_PATH="$(python -c 'import site; print(site.getsitepackages()[0])'):${CMAKE_PREFIX_PATH}" && \
uv pip install --no-build-isolation arctic-inference==0.1.1
ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/"
@@ -69,33 +88,32 @@ RUN --mount=type=bind,source=.git,target=.git \
ENV VLLM_TARGET_DEVICE=xpu
ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
RUN --mount=type=cache,target=/root/.cache/pip \
RUN --mount=type=cache,target=/root/.cache/uv \
--mount=type=bind,source=.git,target=.git \
pip install --no-build-isolation .
uv pip install --no-build-isolation .
CMD ["/bin/bash"]
FROM vllm-base AS vllm-openai
# install additional dependencies for openai api server
RUN --mount=type=cache,target=/root/.cache/pip \
pip install accelerate hf_transfer pytest pytest_asyncio lm_eval[api] modelscope
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install accelerate hf_transfer pytest pytest_asyncio lm_eval[api] modelscope
# install development dependencies (for testing)
RUN python3 -m pip install -e tests/vllm_test_utils
RUN uv pip install -e tests/vllm_test_utils
# install nixl from source code
ENV NIXL_VERSION=0.7.0
RUN python3 /workspace/vllm/tools/install_nixl_from_source_ubuntu.py
RUN python /workspace/vllm/tools/install_nixl_from_source_ubuntu.py
# FIX triton
RUN --mount=type=cache,target=/root/.cache/pip pip uninstall triton triton-xpu -y && pip install triton-xpu==3.6.0 --extra-index-url=https://download.pytorch.org/whl/xpu
# PyJWT-2.7.0 will influence some wheel behaviors, remove its dist-info to avoid conflicts
RUN rm /usr/lib/python3/dist-packages/PyJWT-2.7.0.dist-info/ -rf
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip uninstall triton triton-xpu && \
uv pip install triton-xpu==3.6.0
# remove torch bundled oneccl to avoid conflicts
RUN --mount=type=cache,target=/root/.cache/pip \
pip uninstall oneccl oneccl-devel -y
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip uninstall oneccl oneccl-devel
ENTRYPOINT ["vllm", "serve"]