36 lines
1.2 KiB
Docker
36 lines
1.2 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=2754231ba3a72f41e62922d1552c33e8f3f6a9d1
|
|
RUN git clone https://github.com/vllm-project/vllm.git /workspace/vllm && \
|
|
cd /workspace/vllm && \
|
|
git checkout ${VLLM_PRECOMPILED_WHEEL_COMMIT} && \
|
|
(uv pip uninstall --system -y vllm || true) && \
|
|
VLLM_USE_PRECOMPILED=1 uv pip install --system -e . && \
|
|
cd ${APP_DIR} && \
|
|
uv pip install --system ".[dev]" && \
|
|
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 []
|