huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-23 07:52:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

install whl

Browse Source 
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
This commit is contained in:
Wang, Yi A 2025-03-11 04:27:05 -07:00
parent 3e7a879773
commit a38e65a9f9
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
Dockerfile_intel
View File

@ -118,9 +118,8 @@ ENV TORCH_LLM_ALLREDUCE=1
ENV CCL_TOPO_FABRIC_VERTEX_CONNECTION_CHECK=0
ENV TORCH_DEVICE_BACKEND_AUTOLOAD=0
RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout f943c4a4852f081d30f46a1b1eec12bde5a66e72
RUN cd intel-extension-for-pytorch && git submodule update --init --recursive && USE_AOT_DEVLIST='pvc,ats-m150' BUILD_SEPARATE_OPS=OFF BUILD_WITH_CPU=OFF USE_XETLA=ON python setup.py install && rm -rf /usr/src/intel-extension-for-pytorch
RUN pip install https://intel-extension-for-pytorch.s3.amazonaws.com/ipex_stable/xpu/oneccl_bind_pt-2.6.0%2Bxpu-cp311-cp311-linux_x86_64.whl
RUN pip install https://intel-extension-for-pytorch.s3.amazonaws.com/ipex_stable/xpu/intel_extension_for_pytorch-2.6.10%2Bxpu-cp311-cp311-linux_x86_64.whl
# Install benchmarker
COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
# Install router