# DeepSeek V4 NVFP4 vLLM + CuTeDSL NVFP4 MoE Kernel
FROM vllm/vllm-openai:nightly-x86_64

# Remove broken nixl_ep (built against CUDA 12, image is CUDA 13)
RUN pip uninstall -y nixl-ep; rm -rf /usr/local/lib/python3.12/dist-packages/nixl_ep

RUN apt-get update && apt-get install -y git screen cmake libcusolver-dev-13-0 libcusparse-dev-13-0 libcublas-dev-13-0 libcurand-dev-13-0 libcufft-dev-13-0 libnvjitlink-dev-13-0 && rm -rf /var/lib/apt/lists/*

# Remove the broken symlink if it exists
RUN rm -f /usr/local/cuda/lib64/libcudrt.so.12

ENV CUDA_HOME=/usr/local/cuda
ENV TORCH_CUDA_ARCH_LIST="10.0"

# Install CuTeDSL (NVFP4 block-scaled GEMM kernel framework)
RUN pip install nvidia-cutlass-dsl==4.5.0 nvidia-cutlass-dsl-libs-base==4.5.0

ARG CACHE_BUSTER=${TIMESTAMP}

# Copy the NVFP4 mega_moe Python kernel (no C++ build needed)
COPY src/ /root/nvfp4-megamoe-kernel/src/
COPY pyproject.toml /root/nvfp4-megamoe-kernel/pyproject.toml
RUN cd /root/nvfp4-megamoe-kernel && pip install -e .

# Copy the CuTeDSL kernel and bridge layer
COPY cutedsl/ /root/nvfp4-megamoe-kernel/cutedsl/

ENV PYTHONPATH="/root/nvfp4-megamoe-kernel:${PYTHONPATH}"