Add Dockerfile + build workflow

.github/workflows/publish.yaml

@@ -28,4 +28,33 @@ jobs:
       # if: startsWith(github.ref, 'refs/tags')
       uses: pypa/gh-action-pypi-publish@release/v1
       with:
-        password: ${{ secrets.PYPI_API_TOKEN }}
+        password: ${{ secrets.PYPI_API_TOKEN }}
+
+  docker:
+    name: Build and push Docker image
+    runs-on: ubuntu-latest
+    needs: build-n-publish
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - 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:
+          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:latest

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3-bullseye
+
+# We need to set the host to 0.0.0.0 to allow outside access
+ENV HOST 0.0.0.0
+
+# Install the package
+RUN apt update && apt install -y libopenblas-dev && LLAMA_OPENBLAS=1 pip install llama-cpp-python[server]
+
+# Run the server
+CMD python3 -m llama_cpp.server

README.md

@@ -66,6 +66,14 @@ python3 -m llama_cpp.server
 
 Navigate to [http://localhost:8000/docs](http://localhost:8000/docs) to see the OpenAPI documentation.
 
+## Docker image
+
+A Docker image is available on [GHCR](https://ghcr.io/abetlen/llama-cpp-python). To run the server:
+
+```bash
+docker run --rm -it -p8000:8000 -v /path/to/models:/models -eMODEL=/models/ggml-model-name.bin ghcr.io/abetlen/llama-cpp-python:latest
+```
+
 ## Low-level API
 
 The low-level API is a direct `ctypes` binding to the C API provided by `llama.cpp`.