mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 10:54:36 +00:00
43 lines
1.5 KiB
Docker
43 lines
1.5 KiB
Docker
ARG UBUNTU_VERSION=22.04
|
|
# This needs to generally match the container host's environment.
|
|
ARG CUDA_VERSION=12.6.0
|
|
# Target the CUDA build image
|
|
ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
|
# Target the CUDA runtime image
|
|
ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
|
|
|
|
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
|
|
|
|
# CUDA architecture to build for (defaults to all supported archs)
|
|
ARG CUDA_DOCKER_ARCH=default
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y build-essential git cmake libcurl4-openssl-dev
|
|
|
|
WORKDIR /app
|
|
|
|
COPY . .
|
|
|
|
# Use the default CUDA archs if not specified
|
|
RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
|
|
export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \
|
|
fi && \
|
|
cmake -B build -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)
|
|
|
|
FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y libcurl4-openssl-dev libgomp1 curl
|
|
|
|
COPY --from=build /app/build/ggml/src/libggml.so /libggml.so
|
|
COPY --from=build /app/build/src/libllama.so /libllama.so
|
|
COPY --from=build /app/build/bin/llama-server /llama-server
|
|
|
|
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
|
ENV LLAMA_ARG_HOST=0.0.0.0
|
|
|
|
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
|
|
|
ENTRYPOINT [ "/llama-server" ]
|