mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-27 03:44:35 +00:00
33 lines
772 B
Docker
33 lines
772 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 ${BASE_CUDA_DEV_CONTAINER} as build
|
||
|
|
|
||
|
|
# Unless otherwise specified, we make a fat build.
|
||
|
|
ARG CUDA_DOCKER_ARCH=all
|
||
|
|
|
||
|
|
RUN apt-get update && \
|
||
|
|
apt-get install -y build-essential
|
||
|
|
|
||
|
|
WORKDIR /app
|
||
|
|
|
||
|
|
COPY . .
|
||
|
|
|
||
|
|
# Set nvcc architecture
|
||
|
|
ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
|
||
|
|
# Enable cuBLAS
|
||
|
|
ENV LLAMA_CUBLAS=1
|
||
|
|
|
||
|
|
RUN make
|
||
|
|
|
||
|
|
FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
|
||
|
|
|
||
|
|
COPY --from=build /app/main /main
|
||
|
|
|
||
|
|
ENTRYPOINT [ "/main" ]
|