llama.cpp/.devops/server-cuda.Dockerfile
Kyle Mistele 39baaf55a1
docker : add server-first container images (#5157)
* feat: add Dockerfiles for each platform that user ./server instead of ./main

* feat: update .github/workflows/docker.yml to build server-first docker containers

* doc: add information about running the server with Docker to README.md

* doc: add information about running with docker to the server README

* doc: update n-gpu-layers to show correct GPU usage

* fix(doc): update container tag from `server` to `server-cuda` for README example on running server container with CUDA
2024-01-28 09:55:31 +02:00

33 lines
782 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 ${BASE_CUDA_DEV_CONTAINER} as build
# Unless otherwise specified, we make a fat build.
ARG CUDA_DOCKER_ARCH=all
RUN apt-get update && \
apt-get install -y build-essential git
WORKDIR /app
COPY . .
# Set nvcc architecture
ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
# Enable cuBLAS
ENV LLAMA_CUBLAS=1
RUN make
FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
COPY --from=build /app/server /server
ENTRYPOINT [ "/server" ]