frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 23:03:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix ppc64le buildkite job (#8309)

Browse Source
This commit is contained in:
sumitd2
2024-09-11 01:28:34 +05:30
committed by GitHub
parent f421f3cefb
commit 02751a7a42
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.buildkite/run-cpu-test-ppc64le.sh
View File

@ -11,8 +11,9 @@ trap remove_docker_container EXIT
remove_docker_container remove_docker_container
# Run the image, setting --shm-size=4g for tensor parallel. # Run the image, setting --shm-size=4g for tensor parallel.
source /etc/environment
#docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test cpu-test #docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test cpu-test
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true --network host -e HF_TOKEN --name cpu-test cpu-test docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true --network host -e HF_TOKEN=$HF_TOKEN --name cpu-test cpu-test
# Run basic model test # Run basic model test
docker exec cpu-test bash -c " docker exec cpu-test bash -c "

5
Dockerfile.ppc64le
View File

@ -4,7 +4,7 @@ USER root
ENV PATH="/usr/local/cargo/bin:$PATH:/opt/conda/bin/" ENV PATH="/usr/local/cargo/bin:$PATH:/opt/conda/bin/"
RUN apt-get update -y && apt-get install -y git wget vim libnuma-dev libsndfile-dev libprotobuf-dev build-essential RUN apt-get update -y && apt-get install -y git wget curl vim libnuma-dev libsndfile-dev libprotobuf-dev build-essential
# Some packages in requirements-cpu are installed here # Some packages in requirements-cpu are installed here
# IBM provides optimized packages for ppc64le processors in the open-ce project for mamba # IBM provides optimized packages for ppc64le processors in the open-ce project for mamba
@ -16,7 +16,7 @@ COPY ./ /workspace/vllm
WORKDIR /workspace/vllm WORKDIR /workspace/vllm
# These packages will be in rocketce eventually # These packages will be in rocketce eventually
RUN pip install -v cmake torch==2.3.1 uvloop==0.20.0 -r requirements-cpu.txt --prefer-binary --extra-index-url https://repo.fury.io/mgiessing RUN pip install -v cmake xformers torch==2.3.1 uvloop==0.20.0 -r requirements-cpu.txt --prefer-binary --extra-index-url https://repo.fury.io/mgiessing
RUN VLLM_TARGET_DEVICE=cpu python3 setup.py install RUN VLLM_TARGET_DEVICE=cpu python3 setup.py install
@ -25,4 +25,3 @@ WORKDIR /workspace/
RUN ln -s /workspace/vllm/tests && ln -s /workspace/vllm/examples && ln -s /workspace/vllm/benchmarks RUN ln -s /workspace/vllm/tests && ln -s /workspace/vllm/examples && ln -s /workspace/vllm/benchmarks
ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"] ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]