Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update ipex to fix incorrect output of mllama in cpu (#2640) 

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
This commit is contained in:
Wang, Yi 2024-10-14 22:32:33 +08:00 committed by GitHub
parent 51f5401893
commit 7a82ddcbd0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 20 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
Dockerfile_intel
View File

@ -112,6 +112,8 @@ ENV PATH=/opt/conda/bin:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/bin:/opt/
ENV CCL_ZE_IPC_EXCHANGE=sockets
ENV CMAKE_PREFIX_PATH=/opt/intel/oneapi/mkl/latest/lib/cmake:/opt/intel/oneapi/compiler/latest
ENV CPATH=/opt/intel/oneapi/mpi/latest/include:/opt/intel/oneapi/ccl/latest/include:/opt/intel/oneapi/mkl/latest/include
ENV TORCH_LLM_ALLREDUCE=1
ENV CCL_TOPO_FABRIC_VERTEX_CONNECTION_CHECK=0
# Install benchmarker
COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
@ -128,12 +130,22 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-ins
curl \
ca-certificates \
make \
g++ \
g++-12 \
gcc-12 \
git \
wget \
cmake \
libnuma-dev
RUN update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-12 12
RUN update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 12
RUN update-alternatives --install /usr/bin/cc cc /usr/bin/gcc 30
RUN update-alternatives --set cc /usr/bin/gcc
RUN update-alternatives --install /usr/bin/c++ c++ /usr/bin/g++ 30
RUN update-alternatives --set c++ /usr/bin/g++
ENV HUGGINGFACE_HUB_CACHE=/data \
HF_HUB_ENABLE_HF_TRANSFER=1 \
PORT=80
@ -165,16 +177,17 @@ RUN case ${TARGETPLATFORM} in \
RUN conda install -c conda-forge gperftools mkl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torch-2.4.0.dev20240612%2Bcpu-cp311-cp311-linux_x86_64.whl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchvision-0.19.0.dev20240612%2Bcpu-cp311-cp311-linux_x86_64.whl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchaudio-2.4.0.dev20240612%2Bcpu-cp311-cp311-linux_x86_64.whl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torch-2.5.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchvision-0.20.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchaudio-2.4.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl
RUN pip install triton py-libnuma
WORKDIR /usr/src
RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout eda7a7c42df6f9a64e0de9c2b69304ee02f2c32a
RUN git clone https://github.com/intel/torch-ccl.git && cd torch-ccl && git checkout ccl_torch_dev_0131
RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout f86e93e4890dc2c989024d148d415c9aa8a1649f
RUN git clone https://github.com/intel/torch-ccl.git && cd torch-ccl && git checkout v2.4.0+cpu+rc0
RUN cd intel-extension-for-pytorch && git submodule sync && git submodule update --init --recursive && python setup.py install