llama.cpp/.devops/llama-server-cuda.Dockerfile

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 GGML_CUDA=1
# Enable cURL
ENV LLAMA_CURL=1
# 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

RUN make -j$(nproc) llama-server

FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime

RUN apt-get update && \
    apt-get install -y libcurl4-openssl-dev libgomp1 curl

COPY --from=build /app/llama-server /llama-server

HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]

ENTRYPOINT [ "/llama-server" ]