forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 2
/
Dockerfile.cpu
34 lines (20 loc) · 1.27 KB
/
Dockerfile.cpu
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
# This vLLM Dockerfile is used to construct image that can build and run vLLM on x86 CPU platform.
FROM ubuntu:22.04 AS cpu-test-1
RUN apt-get update -y \
&& apt-get install -y git wget vim numactl gcc-12 g++-12 python3 python3-pip libtcmalloc-minimal4 \
&& update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12
RUN echo 'export LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:$LD_PRELOAD' >> ~/.bashrc
RUN pip install https://intel-extension-for-pytorch.s3.amazonaws.com/ipex_dev/cpu/intel_extension_for_pytorch-2.3.100%2Bgit0eb3473-cp310-cp310-linux_x86_64.whl
RUN pip install --upgrade pip \
&& pip install wheel packaging ninja "setuptools>=49.4.0" numpy
FROM cpu-test-1 AS build
COPY ./ /workspace/vllm
WORKDIR /workspace/vllm
RUN pip install -v -r requirements-cpu.txt --extra-index-url https://download.pytorch.org/whl/cpu
# Support for building with non-AVX512 vLLM: docker build --build-arg VLLM_CPU_DISABLE_AVX512="true" ...
ARG VLLM_CPU_DISABLE_AVX512
ENV VLLM_CPU_DISABLE_AVX512=${VLLM_CPU_DISABLE_AVX512}
RUN VLLM_TARGET_DEVICE=cpu python3 setup.py install
WORKDIR /workspace/
RUN ln -s /workspace/vllm/tests && ln -s /workspace/vllm/examples && ln -s /workspace/vllm/benchmarks
CMD ["/bin/bash"]