ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Update to b17 image (#13085)

Browse source 
* update vllm patch

* fix

* fix triton

---------

Co-authored-by: gc-fu <guancheng.fu@intel.com>
This commit is contained in:
Shaojun Liu 2025-04-17 16:18:22 +08:00 committed by GitHub
parent db5edba786
commit 73198d5b80
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 850 additions and 122 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
docker/llm/serving/xpu/docker/Dockerfile
View file

@ -168,6 +168,10 @@ RUN set -eux && \
mkdir -p /llm && \ mkdir -p /llm && \
cd /llm && \ cd /llm && \
rm -rf /tmp/neo && \ rm -rf /tmp/neo && \
# Install intel_extension_for_pytorch
pip install intel-extension-for-pytorch==2.6.10+xpu --extra-index-url=https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ && \
pip uninstall -y oneccl oneccl-devel && \
pip install intel-opencl-rt==2025.0.2 intel-openmp==2025.0.2 && \
# #
# Install vllm # Install vllm
git clone -b v0.6.6.post1 https://github.com/vllm-project/vllm /llm/vllm && \ git clone -b v0.6.6.post1 https://github.com/vllm-project/vllm /llm/vllm && \

968
docker/llm/serving/xpu/docker/vllm_for_multi_arc.patch
View file

File diff suppressed because it is too large Load diff