louis_lifu
/
vllm
mirror of https://github.com/vllm-project/vllm
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[CI/Build] Dockerfile.cpu improvements (#7298)

This commit is contained in:
Daniele 2024-08-08 21:24:52 +02:00 committed by GitHub
parent e14fb22e59
commit e904576743
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 24 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.dockerignore
View File

@ -1 +1,4 @@
vllm/*.so
/.venv
/build
dist

30
Dockerfile.cpu
View File

@ -2,14 +2,16 @@
FROM ubuntu:22.04 AS cpu-test-1
RUN apt-get update -y \
&& apt-get install -y curl git wget vim numactl gcc-12 g++-12 python3 python3-pip libtcmalloc-minimal4 libnuma-dev \
RUN --mount=type=cache,target=/var/cache/apt \
apt-get update -y \
&& apt-get install -y curl ccache git wget vim numactl gcc-12 g++-12 python3 python3-pip libtcmalloc-minimal4 libnuma-dev \
&& update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12
# https://intel.github.io/intel-extension-for-pytorch/cpu/latest/tutorials/performance_tuning/tuning_guide.html
# intel-openmp provides additional performance improvement vs. openmp
# tcmalloc provides better memory allocation efficiency, e.g, holding memory in caches to speed up access of commonly-used objects.
RUN pip install intel-openmp
RUN --mount=type=cache,target=/root/.cache/pip \
pip install intel-openmp
ENV LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/usr/local/lib/libiomp5.so:$LD_PRELOAD"
@ -17,22 +19,32 @@ RUN echo 'ulimit -c 0' >> ~/.bashrc
RUN pip install https://intel-extension-for-pytorch.s3.amazonaws.com/ipex_dev/cpu/intel_extension_for_pytorch-2.4.0%2Bgitfbaa4bc-cp310-cp310-linux_x86_64.whl
RUN pip install --upgrade pip \
&& pip install wheel packaging ninja "setuptools>=49.4.0" numpy
ENV PIP_EXTRA_INDEX_URL=https://download.pytorch.org/whl/cpu
RUN --mount=type=cache,target=/root/.cache/pip \
--mount=type=bind,src=requirements-build.txt,target=requirements-build.txt \
pip install --upgrade pip && \
pip install -r requirements-build.txt
FROM cpu-test-1 AS build
COPY ./ /workspace/vllm
WORKDIR /workspace/vllm
RUN pip install -v -r requirements-cpu.txt --extra-index-url https://download.pytorch.org/whl/cpu
RUN --mount=type=cache,target=/root/.cache/pip \
--mount=type=bind,src=requirements-common.txt,target=requirements-common.txt \
--mount=type=bind,src=requirements-cpu.txt,target=requirements-cpu.txt \
pip install -v -r requirements-cpu.txt
COPY ./ ./
# Support for building with non-AVX512 vLLM: docker build --build-arg VLLM_CPU_DISABLE_AVX512="true" ...
ARG VLLM_CPU_DISABLE_AVX512
ENV VLLM_CPU_DISABLE_AVX512=${VLLM_CPU_DISABLE_AVX512}
RUN VLLM_TARGET_DEVICE=cpu python3 setup.py install
ENV CCACHE_DIR=/root/.cache/ccache
RUN --mount=type=cache,target=/root/.cache/pip \
--mount=type=cache,target=/root/.cache/ccache \
VLLM_TARGET_DEVICE=cpu python3 setup.py bdist_wheel && \
pip install dist/*.whl
WORKDIR /workspace/