vllm-omni/docker/Dockerfile.npu

ARG VLLM_ASCEND_IMAGE=quay.io/atlas-ci/vllm-ascend
ARG VLLM_ASCEND_VERSION=v0.29.0
ARG VLLM_ASCEND_DEVICE_SUFFIX=
FROM ${VLLM_ASCEND_IMAGE}:${VLLM_ASCEND_VERSION}${VLLM_ASCEND_DEVICE_SUFFIX}

ARG APP_DIR=/vllm-workspace/vllm-omni
WORKDIR ${APP_DIR}
COPY . .

RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
    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 -v "mindiesd==3.1.0" && \
    python3 -m pip install -v -e /vllm-workspace/vllm-omni/ --no-build-isolation

RUN python3 -m pip install -v --no-deps \
      "stepaudio2-minicpmo>=0.1.1" \
      "step-audio2>=1.0.0"

ENV VLLM_TARGET_DEVICE=npu
ENV VLLM_WORKER_MULTIPROC_METHOD=spawn

ENTRYPOINT []