forked from EngineX-Cambricon/enginex-mlu370-vllm
19 lines
508 B
Docker
19 lines
508 B
Docker
FROM vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest
|
|
|
|
COPY ./ /workspace/vllm
|
|
|
|
WORKDIR /workspace/vllm
|
|
|
|
RUN pip install -v -r requirements-hpu.txt
|
|
|
|
ENV no_proxy=localhost,127.0.0.1
|
|
ENV PT_HPU_ENABLE_LAZY_COLLECTIVES=true
|
|
|
|
RUN VLLM_TARGET_DEVICE=hpu python3 setup.py install
|
|
|
|
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"]
|