# syntax=docker/dockerfile:1
FROM nvidia/cuda:13.1.0-devel-ubuntu26.04 AS base

RUN apt-get update && apt-get install -y --no-install-recommends \
    python3 python3-pip python3-dev python3-venv \
    gcc g++ \
    wget curl jq \
    && rm -rf /var/lib/apt/lists/*

RUN ln -sf /usr/bin/python3 /usr/bin/python

RUN pip3 install --no-cache-dir vllm

RUN python3 -c "import vllm; print('vLLM', vllm.__version__)"

FROM base AS runtime

ENV CC=/usr/bin/gcc
ENV CUDA_HOME=/usr/local/cuda-13.1
ENV VLLM_USE_FLASHINFER_SAMPLER=1
ENV TORCH_MATMUL_PRECISION=high
ENV PATH=/usr/local/cuda-13.1/bin:/usr/local/bin:/usr/bin:/bin

EXPOSE 8000

COPY entrypoint.sh /entrypoint.sh
RUN chmod +x /entrypoint.sh

ENTRYPOINT ["/entrypoint.sh"]
CMD []