Skip to content

[Add] support for BMG in intelanalytics/ipex-llm-serving-xpu docker image #12926

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

[Add] support for BMG in intelanalytics/ipex-llm-serving-xpu docker image #12926

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
9cfa9b0
update bmg24 compute runtime
ACupofAir Mar 3, 2025
4b6bbc7
update bmg24 compute runtime
ACupofAir Mar 3, 2025
c6e13bb
update bmg24 compute runtime
ACupofAir Mar 3, 2025
d7aaf24
update bmg24 compute runtime
ACupofAir Mar 3, 2025
4b6a2a7
Merge branch 'junwang-bmg-docker' of https://github.com/ACupofAir/Big…
ACupofAir Mar 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 53 additions & 2 deletions docker/llm/serving/xpu/docker/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,7 +161,58 @@ RUN set -eux && \
VLLM_TARGET_DEVICE=xpu pip install --no-build-isolation -v /llm/vllm && \
pip install mpi4py fastapi uvicorn openai && \
pip install gradio==4.43.0 && \
pip install ray

pip install ray && \
#
# Install compute runtime for BMG 24G
# Install igc
apt-get install -y --no-install-recommends bison flex python3-mako && \
mkdir -p /tmp/igc && \
cd /tmp/igc && \
git clone https://github.com/intel/vc-intrinsics vc-intrinsics && \
git clone -b llvmorg-14.0.5 https://github.com/llvm/llvm-project llvm-project && \
git clone -b ocl-open-140 https://github.com/intel/opencl-clang llvm-project/llvm/projects/opencl-clang && \
git clone -b llvm_release_140 https://github.com/KhronosGroup/SPIRV-LLVM-Translator llvm-project/llvm/projects/llvm-spirv && \
git clone https://github.com/KhronosGroup/SPIRV-Tools.git SPIRV-Tools && \
git clone https://github.com/KhronosGroup/SPIRV-Headers.git SPIRV-Headers && \
git clone https://github.com/intel/intel-graphics-compiler igc && \
git config --global user.email "[email protected]" &&\
git config --global user.name "IPEX-LLM" && \
cd igc && \
mkdir build && cd build && \
cmake ../ && \
make -j32 && make install -j32 && \
cd /tmp && rm -rf /tmp/igc && \
#
apt-get install -y --no-install-recommends libigdgmm-dev libigdgmm12 unzip clinfo pciutils && \
# Install gmmlib
git clone https://github.com/intel/gmmlib.git && \
cd gmmlib && \
mkdir build && cd build && \
cmake ../ -DCMAKE_INSTALL_PREFIX=/usr && \
make -j32 && make install && \
cd /tmp && rm -rf /tmp/gmmlib && \
# Install level-zero
git clone https://github.com/oneapi-src/level-zero.git && \
cd level-zero && \
mkdir build && cd build && \
cmake ../ -DCMAKE_INSTALL_PREFIX=/usr && \
make -j32 && make install && \
cd /tmp && rm -rf /tmp/level-zero && \
# Install compute-runtime
wget https://github.com/intel/compute-runtime/archive/refs/tags/24.52.32224.5.zip && \
unzip 24.52.32224.5.zip && \
cd compute-runtime-24.52.32224.5 && \
sed -i '13a \
DEVICE(0xE210, BmgHwConfig) \
DEVICE(0xE212, BmgHwConfig) \
DEVICE(0xE215, BmgHwConfig) \
DEVICE(0xE216, BmgHwConfig)' ./shared/source/dll/devices/devices_base.inl && \
sed -i '13s/\(bmgG21DeviceIds{[^}]*\)}/\1, 0xE210, 0xE212, 0xE215, 0xE216}/' ./shared/source/xe2_hpg_core/bmg/definitions/device_ids_configs_bmg.h && \
mkdir build && cd build && \
cmake ../ -DSKIP_UNIT_TESTS=ON && \
make -j32 && make install && \
cd /llm && \
rm -rf /tmp/compute-runtime-24.52.32224.5 && \
rm -rf /tmp/24.52.32224.5.zip
WORKDIR /llm/
ENTRYPOINT ["bash", "/llm/start-vllm-service.sh"]