vllm/Dockerfile.xpu

FROM intel/oneapi-basekit:2024.2.1-0-devel-ubuntu22.04 AS vllm-base

RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/intel-oneapi-archive-keyring.gpg > /dev/null && \
    echo "deb [signed-by=/usr/share/keyrings/intel-oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main " | tee /etc/apt/sources.list.d/oneAPI.list && \
    chmod 644 /usr/share/keyrings/intel-oneapi-archive-keyring.gpg && \
    wget -O- https://repositories.intel.com/graphics/intel-graphics.key | gpg --dearmor | tee /usr/share/keyrings/intel-graphics.gpg > /dev/null && \
    echo "deb [arch=amd64,i386 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/graphics/ubuntu jammy arc" | tee /etc/apt/sources.list.d/intel.gpu.jammy.list && \
    chmod 644 /usr/share/keyrings/intel-graphics.gpg

RUN apt-get update -y && \
    apt-get install -y --no-install-recommends --fix-missing \
    curl \
    ffmpeg \
    git \
    libsndfile1 \
    libsm6 \
    libxext6 \
    libgl1 \
    lsb-release \
    numactl \
    python3 \
    python3-dev \
    python3-pip \
    # vim \
    wget

WORKDIR /workspace/vllm
COPY requirements/xpu.txt /workspace/vllm/requirements/xpu.txt
COPY requirements/common.txt /workspace/vllm/requirements/common.txt

RUN --mount=type=cache,target=/root/.cache/pip \
    pip install --no-cache-dir \
    -r requirements/xpu.txt

RUN git clone https://github.com/intel/pti-gpu && \
    cd pti-gpu/sdk && \
    git checkout 6c491f07a777ed872c2654ca9942f1d0dde0a082 && \
    mkdir build && \
    cd build && \
    cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_TOOLCHAIN_FILE=../cmake/toolchains/icpx_toolchain.cmake -DBUILD_TESTING=OFF .. && \
    make -j && \
    cmake --install . --config Release --prefix "/usr/local"

ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/"

COPY . .
ARG GIT_REPO_CHECK
RUN --mount=type=bind,source=.git,target=.git \
    if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh; fi

ENV VLLM_TARGET_DEVICE=xpu

RUN --mount=type=cache,target=/root/.cache/pip \
    --mount=type=bind,source=.git,target=.git \
    python3 setup.py install

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 'modelscope!=1.15.0'

ENV VLLM_USAGE_SOURCE production-docker-image \
    TRITON_XPU_PROFILE 1
# install development dependencies (for testing)
RUN python3 -m pip install -e tests/vllm_test_utils
ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]