tags: ghcr.io/abetlen/llama-cpp-python:latest

docker-cuda:

name: Build and push Docker image

runs-on: ubuntu-latest

steps:

- name: Checkout

uses: actions/checkout@v3

with:

submodules: "true"

- name: Set up QEMU

uses: docker/setup-qemu-action@v2

- name: Set up Docker Buildx

uses: docker/setup-buildx-action@v2

- name: Login to GitHub Container Registry

uses: docker/login-action@v2

with:

registry: ghcr.io

username: ${{ github.repository_owner }}

password: ${{ secrets.GITHUB_TOKEN }}

- name: Build and push

uses: docker/build-push-action@v4

with:

file: Dockerfile.cuda

context: .

push: true # push to registry

pull: true # always fetch the latest base images

platforms: linux/amd64,linux/arm64 # build for both amd64 and arm64

tags: ghcr.io/abetlen/llama-cpp-python-cuda:latest

FROM nvidia/cuda:12.1.1-devel-ubuntu20.04

# We need to set the host to 0.0.0.0 to allow outside access

ENV HOST 0.0.0.0

COPY . .

# Install the package

RUN apt update && apt install -y python3 python3-pip

RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette

RUN LLAMA_CUBLAS=1 python3 setup.py develop

# Run the server

CMD python3 -m llama_cpp.server