Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
OpenDAS
text-generation-inference
Commits
7a82ddcb
Unverified
Commit
7a82ddcb
authored
Oct 14, 2024
by
Wang, Yi
Committed by
GitHub
Oct 14, 2024
Browse files
update ipex to fix incorrect output of mllama in cpu (#2640)
Signed-off-by:
Wang, Yi A
<
yi.a.wang@intel.com
>
parent
51f54018
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
20 additions
and
7 deletions
+20
-7
Dockerfile_intel
Dockerfile_intel
+20
-7
No files found.
Dockerfile_intel
View file @
7a82ddcb
...
...
@@ -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
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment