FROM docker.io/nvidia/cuda:12.8.0-devel-rockylinux9 AS builder
RUN dnf install -y cmake gcc-c++ && dnf clean all
ENV TMPDIR=/llama.cpp/tmp

# Copy local source with inline MTP changes
COPY . /llama.cpp
RUN cd /llama.cpp && \
    mkdir -p /llama.cpp/tmp && \
    cmake -B build -DGGML_CUDA=ON -DBUILD_SHARED_LIBS=OFF -DCMAKE_CUDA_ARCHITECTURES=120 -DLLAMA_BUILD_TESTS=OFF && \
    cmake --build build --target llama-server llama-cli --config Release -j5

FROM docker.io/nvidia/cuda:12.8.0-runtime-rockylinux9
COPY --from=builder /llama.cpp/build/bin/llama-server /usr/local/bin/
COPY --from=builder /llama.cpp/build/bin/llama-cli /usr/local/bin/
RUN mkdir -p /models /templates
EXPOSE 8000
ENTRYPOINT ["/entrypoint.sh"]