FROM vllm/vllm-openai@sha256:61fc8a896b0a4fbbbdc063bc4b0dbc25ce98e02b5050c24aeb7830ac02039b14

# Preserve the pinned vLLM/PyTorch/CUDA/CUTLASS/Triton stack.
COPY requirements.txt /opt/naive/requirements.txt
RUN python3 -m pip install --no-cache-dir --no-deps --target /opt/naive-python -r /opt/naive/requirements.txt \
    && python3 -m pip install --no-cache-dir --no-deps --target /opt/flashinfer-v070 flashinfer-python==0.7.0
COPY scripts/ /opt/naive/scripts/
COPY sitecustomize.py /opt/naive-python/sitecustomize.py
COPY pyproject.toml /opt/vllm-naive/pyproject.toml
COPY vllm_naive/ /opt/vllm-naive/vllm_naive/
RUN python3 -m pip install --no-deps --no-build-isolation /opt/vllm-naive
ENV PYTHONPATH=/opt/flashinfer-v070:/opt/naive-python:/opt/naive/scripts \
    NAIVE_FLASHINFER_SOURCE_ONLY=1 \
    NAIVE_EXPERT_BACKEND=fused \
    FLASHINFER_WORKSPACE_BASE=/cache/flashinfer-v070 \
    HF_MODULES_CACHE=/cache/hf-modules \
    TORCH_EXTENSIONS_DIR=/cache/torch-extensions \
    TRITON_CACHE_DIR=/cache/triton \
    XDG_CACHE_HOME=/cache/xdg \
    HF_HUB_OFFLINE=1 \
    TRANSFORMERS_OFFLINE=1 \
    OMP_NUM_THREADS=1 \
    NCCL_P2P_DISABLE=1 \
    VLLM_PLUGINS=naive_n05 \
    VLLM_WORKER_MULTIPROC_METHOD=spawn \
    VLLM_CACHE_ROOT=/cache/vllm \
    VLLM_FLOAT32_MATMUL_PRECISION=highest
WORKDIR /opt/naive
ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]