frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

ppc64le: Dockerfile fixed, and a script for buildkite (#8026)

Browse Source
This commit is contained in:
sumitd2
2024-09-07 23:48:40 +05:30
committed by GitHub
parent 36bf8150cc
commit b962ee1470
2 changed files with 43 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
.buildkite/run-cpu-test-ppc64le.sh Executable file
View File

@ -0,0 +1,32 @@
# This script build the CPU docker image and run the offline inference inside the container.
# It serves a sanity check for compilation and basic model usage.
set -ex
# Try building the docker image
docker build -t cpu-test -f Dockerfile.ppc64le .
# Setup cleanup
remove_docker_container() { docker rm -f cpu-test || true; }
trap remove_docker_container EXIT
remove_docker_container
# Run the image, setting --shm-size=4g for tensor parallel.
#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
# Run basic model test
docker exec cpu-test bash -c "
pip install pytest matplotlib einops transformers_stream_generator
pytest -v -s tests/models -m \"not vlm\" --ignore=tests/models/test_embedding.py --ignore=tests/models/test_oot_registration.py --ignore=tests/models/test_registry.py --ignore=tests/models/test_jamba.py --ignore=tests/models/test_danube3_4b.py" # Mamba and Danube3-4B on CPU is not supported
# online inference
docker exec cpu-test bash -c "
python3 -m vllm.entrypoints.openai.api_server --model facebook/opt-125m &
timeout 600 bash -c 'until curl localhost:8000/v1/models; do sleep 1; done' || exit 1
python3 benchmarks/benchmark_serving.py \
--backend vllm \
--dataset-name random \
--model facebook/opt-125m \
--num-prompts 20 \
--endpoint /v1/completions \
--tokenizer facebook/opt-125m"

16
Dockerfile.ppc64le
View File

@ -2,21 +2,27 @@ FROM mambaorg/micromamba
ARG MAMBA_DOCKERFILE_ACTIVATE=1
USER root
RUN apt-get update -y && apt-get install -y git wget vim numactl gcc-12 g++-12 protobuf-compiler libprotobuf-dev && update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12
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
# Some packages in requirements-cpu are installed here
# IBM provides optimized packages for ppc64le processors in the open-ce project for mamba
# Currently these may not be available for venv or pip directly
RUN micromamba install -y -n base -c https://ftp.osuosl.org/pub/open-ce/1.11.0-p10/ -c defaults python=3.10 pytorch-cpu=2.1.2 torchvision-cpu=0.16.2 && micromamba clean --all --yes
RUN micromamba install -y -n base -c https://ftp.osuosl.org/pub/open-ce/1.11.0-p10/ -c defaults python=3.10 torchvision-cpu=0.16.2 rust && micromamba clean --all --yes
COPY ./ /workspace/vllm
WORKDIR /workspace/vllm
# These packages will be in rocketce eventually
RUN pip install -v -r requirements-cpu.txt --prefer-binary --extra-index-url https://repo.fury.io/mgiessing
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 VLLM_TARGET_DEVICE=cpu python3 setup.py install
WORKDIR /vllm-workspace
ENTRYPOINT ["/opt/conda/bin/python3", "-m", "vllm.entrypoints.openai.api_server"]
WORKDIR /workspace/
RUN ln -s /workspace/vllm/tests && ln -s /workspace/vllm/examples && ln -s /workspace/vllm/benchmarks
ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]