huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-06-11 03:42:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Attempt to fix intel CPU.

Browse Source
This commit is contained in:
Nicolas Patry 2025-02-06 16:53:40 +01:00
parent dc2e3e5ded
commit 072082774e
No known key found for this signature in database
GPG Key ID: 3942D952A9BD2F09
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
Dockerfile_intel
View File

@ -110,9 +110,16 @@ COPY server server
COPY server/Makefile server/Makefile
ENV UV_SYSTEM_PYTHON=1
RUN cd server && \
make gen-server && \
pip install -U pip uv && \
uv pip install -e ".[accelerate, compressed-tensors, peft, outlines]" --no-cache-dir
uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines --no-install-project && \
. ./.venv/bin/activate && \
make gen-server-raw
RUN cd server && \
uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines && \
. ./.venv/bin/activate && \
pwd && \
text-generation-server --help
ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/intel/oneapi/pti/0.9/lib:/opt/conda/lib
ENV CCL_ZE_IPC_EXCHANGE=sockets
@ -121,7 +128,7 @@ ENV CCL_ZE_IPC_EXCHANGE=sockets
ENV TORCH_DEVICE_BACKEND_AUTOLOAD=0
RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout 1ccf72b2d11cd00b47aef6d6cd054c088aa6f083
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 ./server/.venv/bin/activate && 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
# Install benchmarker
COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark