llama.cpp/.devops/server-cuda.Dockerfile
slaren 2d08b7fbb4
docker : build only main and server in their images (#7782)
* add openmp lib to dockerfiles

* build only main and server in their docker images
2024-06-06 08:19:49 +03:00

38 lines
926 B
Docker

ARG UBUNTU_VERSION=22.04
# This needs to generally match the container host's environment.
ARG CUDA_VERSION=11.7.1
# 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 ${BASE_CUDA_DEV_CONTAINER} as build
# Unless otherwise specified, we make a fat build.
ARG CUDA_DOCKER_ARCH=all
RUN apt-get update && \
apt-get install -y build-essential git libcurl4-openssl-dev
WORKDIR /app
COPY . .
# Set nvcc architecture
ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
# Enable CUDA
ENV LLAMA_CUDA=1
# Enable cURL
ENV LLAMA_CURL=1
RUN make -j$(nproc) server
FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
RUN apt-get update && \
apt-get install -y libcurl4-openssl-dev libgomp1
COPY --from=build /app/server /server
ENTRYPOINT [ "/server" ]