# Phase 1: Pull prebuilt binaries FROM ghcr.io/ggml-org/llama.cpp:full-cuda AS llama-bin # Phase 2: Building environment FROM nvidia/cuda:12.6.3-devel-ubuntu24.04 ENV DEBIAN_FRONTEND=noninteractive \ CMAKE_GENERATOR=Ninja \ APP_ROOT=/workspace/app \ BUILD_DIR=/workspace/app/build RUN apt-get update && apt-get install -y --no-install-recommends \ build-essential \ ca-certificates \ curl \ git \ libboost-json-dev \ libboost-program-options-dev \ libssl-dev \ ninja-build \ pkg-config \ zlib1g-dev \ && rm -rf /var/lib/apt/lists/* # Install modern CMake via curl (Ubuntu 24.04 'apt' version can be laggy) RUN curl -L https://github.com/Kitware/CMake/releases/download/v3.31.0/cmake-3.31.0-linux-x86_64.sh -o cmake.sh && \ sh cmake.sh --skip-license --prefix=/usr/local && rm cmake.sh # Copy backends to /usr/local/lib and register with ldconfig so the # runtime linker can resolve libllama.so, libggml.so, libggml-base.so etc. COPY --from=llama-bin /app/lib*.so* /usr/local/lib/ RUN ldconfig # Headers for C++ Build RUN git clone --depth 1 -b b9012 https://github.com/ggml-org/llama.cpp.git /tmp/llama-src && \ cp -r /tmp/llama-src/include/* /usr/local/include/ && \ cp -r /tmp/llama-src/ggml/include/* /usr/local/include/ && \ rm -rf /tmp/llama-src ENV LD_LIBRARY_PATH="/usr/local/lib:${LD_LIBRARY_PATH}" WORKDIR /workspace/app COPY . . # Build the C++ pipeline RUN cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release && \ cmake --build build -j$(nproc) # Co-locate GGML backend plugins with the executable. # ggml_backend_load_all() searches the executable directory first when # GGML_BACKEND_DIR is not set. Copying the ggml-*.so plugin files here # ensures the loader finds them without any environment variable. # libllama.so, libggml.so, and libggml-base.so are NOT copied here — # those are proper shared libraries resolved via ldconfig/LD_LIBRARY_PATH. RUN cp /usr/local/lib/libggml-cuda.so /workspace/app/build/ 2>/dev/null || true && \ cp /usr/local/lib/libggml-cpu*.so /workspace/app/build/ 2>/dev/null || true && \ cp /usr/local/lib/libggml-blas*.so /workspace/app/build/ 2>/dev/null || true && \ cp /usr/local/lib/libggml-rpc*.so /workspace/app/build/ 2>/dev/null || true # Setup Start Script COPY runpod/start.sh /usr/local/bin/biergarten-start RUN chmod +x /usr/local/bin/biergarten-start WORKDIR /workspace/app/build ENTRYPOINT ["/usr/local/bin/biergarten-start"]