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

use oneapi 2024 docker image directly for xpu (#2793) 

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
This commit is contained in:
Wang, Yi 2024-12-06 12:06:23 +08:00 committed by GitHub
parent e0db633396
commit 6685e8fcda
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
Dockerfile_intel
View File

@ -45,7 +45,7 @@ RUN cargo build --profile release-opt --frozen
# Text Generation Inference base image for Intel
FROM intel/intel-extension-for-pytorch:2.3.110-xpu AS xpu
FROM intel/oneapi-basekit:2024.2.1-0-devel-ubuntu22.04 AS xpu
USER root
@ -87,7 +87,7 @@ RUN echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https:/
RUN mv /tmp/intel-for-pytorch-gpu-dev.list /etc/apt/sources.list.d
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt install -y intel-basekit=2024.2.1-98 xpu-smi cmake ninja-build pciutils intel-pti-dev-0.9
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt install -y xpu-smi cmake ninja-build pciutils intel-pti-dev-0.9
# Text Generation Inference base env
ENV HF_HOME=/data \
@ -114,15 +114,8 @@ RUN cd server && \
pip install -r requirements_intel.txt && \
pip install ".[accelerate, compressed-tensors, peft, outlines]" --no-cache-dir
ENV CCL_ROOT=/opt/intel/oneapi/ccl/latest
ENV I_MPI_ROOT=/opt/intel/oneapi/mpi/latest
ENV FI_PROVIDER_PATH=/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/lib/prov:/usr/lib/x86_64-linux-gnu/libfabric
ENV LIBRARY_PATH=/opt/intel/oneapi/mpi/latest/lib:/opt/intel/oneapi/ccl/latest/lib/:/opt/intel/oneapi/mkl/latest/lib/:/opt/intel/oneapi/compiler/latest/lib
ENV LD_LIBRARY_PATH=/opt/intel/oneapi/ccl/latest/lib/:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/lib:/opt/intel/oneapi/mpi/latest/lib:/opt/intel/oneapi/mkl/latest/lib:/opt/intel/oneapi/compiler/latest/opt/compiler/lib:/opt/intel/oneapi/compiler/latest/lib:/opt/intel/oneapi/lib:/opt/intel/oneapi/lib/intel64:/opt/intel/oneapi/pti/0.9/lib:/opt/conda/lib
ENV PATH=/opt/conda/bin:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/bin:/opt/intel/oneapi/mpi/latest/bin:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/bin:/opt/intel/oneapi/mkl/latest/bin/:/opt/intel/oneapi/compiler/latest/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/intel/oneapi/pti/0.9/lib:/opt/conda/lib
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