40 lines
1.7 KiB
Docker
40 lines
1.7 KiB
Docker
ARG VLLM_ASCEND_IMAGE=quay.io/ascend/vllm-ascend
|
|
ARG VLLM_ASCEND_TAG=v0.17.0rc1
|
|
FROM ${VLLM_ASCEND_IMAGE}:${VLLM_ASCEND_TAG}
|
|
|
|
WORKDIR /vllm-workspace/vllm
|
|
RUN git fetch origin --tags && git checkout v0.18.0
|
|
|
|
RUN git config --global url."https://gh-proxy.test.osinfra.cn/https://github.com/".insteadOf "https://github.com/"
|
|
|
|
WORKDIR /vllm-workspace/vllm-ascend
|
|
RUN git fetch origin releases/v0.18.0 && git checkout d781902ce9dbda8ab1e11bb0f2f0c1bc508fee7a
|
|
# Install vllm-ascend
|
|
RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
|
|
source /usr/local/Ascend/nnal/atb/set_env.sh && \
|
|
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
|
|
python3 -m pip install -U pip && \
|
|
python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ \
|
|
--index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple \
|
|
--extra-index https://download.pytorch.org/whl/cpu/ \
|
|
--trusted-host cache-service.nginx-pypi-cache.svc.cluster.local \
|
|
--default-timeout=60
|
|
python3 -m pip cache purge
|
|
|
|
ARG APP_DIR=/vllm-workspace/vllm-omni
|
|
WORKDIR ${APP_DIR}
|
|
COPY . .
|
|
|
|
RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
|
|
source /usr/local/Ascend/nnal/atb/set_env.sh && \
|
|
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
|
|
python3 -m pip install -U pip && \
|
|
python3 -m pip install -v -e /vllm-workspace/vllm-omni/ --no-build-isolation \
|
|
--index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple \
|
|
--trusted-host cache-service.nginx-pypi-cache.svc.cluster.local \
|
|
--default-timeout=60
|
|
|
|
ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
|
|
ENTRYPOINT []
|