|
ARG UBUNTU_VERSION=22.04 |
|
|
|
ARG CUDA_VERSION=12.6.0 |
|
|
|
ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION} |
|
|
|
ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION} |
|
|
|
FROM ${BASE_CUDA_DEV_CONTAINER} AS build |
|
|
|
|
|
ARG CUDA_DOCKER_ARCH=default |
|
|
|
RUN apt-get update && \ |
|
apt-get install -y build-essential git cmake libcurl4-openssl-dev |
|
|
|
WORKDIR /app |
|
|
|
COPY . . |
|
|
|
|
|
RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \ |
|
export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \ |
|
fi && \ |
|
cmake -B build -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \ |
|
cmake --build build --config Release --target llama-server -j$(nproc) && \ |
|
mkdir -p /app/lib && \ |
|
find build -name "*.so" -exec cp {} /app/lib \; |
|
|
|
FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime |
|
|
|
RUN apt-get update && \ |
|
apt-get install -y libcurl4-openssl-dev libgomp1 curl |
|
|
|
COPY --from=build /app/lib/ / |
|
COPY --from=build /app/build/bin/llama-server /llama-server |
|
|
|
|
|
ENV LLAMA_ARG_HOST=0.0.0.0 |
|
|
|
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ] |
|
|
|
ENTRYPOINT [ "/llama-server" ] |
|
|