33 lines
1.0 KiB
Docker
33 lines
1.0 KiB
Docker
ARG VLLM_BASE_IMAGE=vllm/vllm-openai
|
|
ARG VLLM_BASE_TAG=v0.17.0
|
|
FROM ${VLLM_BASE_IMAGE}:${VLLM_BASE_TAG}
|
|
ARG APP_DIR=/workspace/vllm-omni
|
|
WORKDIR ${APP_DIR}
|
|
COPY . .
|
|
|
|
# Install system dependencies
|
|
RUN apt-get update && \
|
|
apt-get install -y espeak-ng ffmpeg git sox libsox-fmt-all jq && \
|
|
apt-get clean && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
RUN uv pip uninstall --system -y vllm || true
|
|
|
|
# Install vLLM from source at the selected commit using precompiled artifacts
|
|
ENV VLLM_PRECOMPILED_WHEEL_COMMIT=0a0a1a198be88e1782b52fa31738896468200a76
|
|
RUN uv pip install --system --force-reinstall --prerelease=allow vllm --extra-index-url https://wheels.vllm.ai/${VLLM_PRECOMPILED_WHEEL_COMMIT}
|
|
|
|
RUN uv pip install --system ".[dev]"
|
|
|
|
RUN uv pip install --system --upgrade \
|
|
"flashinfer-cubin==0.6.6" \
|
|
"nvidia-cublas-cu12==12.9.1.4" \
|
|
"numpy==2.2.6"
|
|
|
|
RUN uv pip install --system --upgrade \
|
|
"flashinfer-jit-cache==0.6.6" \
|
|
--index-url https://flashinfer.ai/whl/cu129
|
|
RUN ln -sf /usr/bin/python3 /usr/bin/python
|
|
|
|
ENTRYPOINT []
|