[WIP] Add a model_server example podman-llm #893
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Model Servers | |
| on: | |
| pull_request: | |
| branches: | |
| - main | |
| paths: | |
| - 'model_servers/**' | |
| - 'models/Makefile' | |
| - .github/workflows/model_servers.yaml | |
| push: | |
| branches: | |
| - main | |
| paths: | |
| - 'model_servers/**' | |
| - 'models/Makefile' | |
| - .github/workflows/model_servers.yaml | |
| workflow_dispatch: | |
| env: | |
| REGISTRY: ghcr.io | |
| REGISTRY_ORG: containers | |
| jobs: | |
| model-servers-buid-and-push: | |
| if: "!contains(github.event.pull_request.labels.*.name, 'hold-tests')" | |
| strategy: | |
| matrix: | |
| include: | |
| - image_name: llamacpp_python | |
| model: granite | |
| flavor: base | |
| directory: llamacpp_python | |
| platforms: linux/amd64,linux/arm64 | |
| no_gpu: 1 | |
| - image_name: llamacpp-python-cuda | |
| model: granite | |
| flavor: cuda | |
| directory: llamacpp_python | |
| platforms: linux/amd64,linux/arm64 | |
| no_gpu: 0 | |
| - image_name: llamacpp-python-vulkan-amd | |
| model: granite | |
| flavor: vulkan/amd64 | |
| directory: llamacpp_python | |
| platforms: linux/amd64 | |
| no_gpu: 0 | |
| - image_name: llamacpp-python-vulkan-arm | |
| model: granite | |
| flavor: vulkan/arm64 | |
| directory: llamacpp_python | |
| platforms: linux/arm64 | |
| no_gpu: 0 | |
| - image_name: whispercpp | |
| model: whisper-small | |
| flavor: base | |
| directory: whispercpp | |
| platforms: linux/amd64,linux/arm64 | |
| no_gpu: 1 | |
| - image_name: object_detection_python | |
| model: facebook-detr-resnet-101 | |
| flavor: base | |
| directory: object_detection_python | |
| platforms: linux/amd64,linux/arm64 | |
| no_gpu: 1 | |
| runs-on: ubuntu-24.04 | |
| permissions: | |
| contents: read | |
| packages: write | |
| services: | |
| registry: | |
| image: registry:2.8.3 | |
| ports: | |
| - 5000:5000 | |
| steps: | |
| - name: Remove unnecessary files | |
| run: | | |
| sudo rm -rf /usr/share/dotnet | |
| sudo rm -rf "$AGENT_TOOLSDIRECTORY" | |
| - uses: actions/[email protected] | |
| - name: Install qemu dependency | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install -y qemu-user-static | |
| - name: Set up Python | |
| uses: actions/[email protected] | |
| with: | |
| python-version: '3.11' | |
| - name: Build Image | |
| id: build_image | |
| uses: redhat-actions/[email protected] | |
| with: | |
| image: ${{ env.REGISTRY }}/${{ github.repository_owner}}/${{ matrix.image_name }} | |
| platforms: ${{ matrix.platforms }} | |
| tags: latest | |
| containerfiles: ./model_servers/${{ matrix.directory }}/${{ matrix.flavor }}/Containerfile | |
| context: model_servers/${{ matrix.directory }}/ | |
| - name: Download model | |
| working-directory: ./models | |
| run: make download-model-${{ matrix.model }} | |
| - name: Install python dependencies | |
| working-directory: ./model_servers/${{ matrix.directory }}/ | |
| run: make install | |
| - name: Run non-gpu tests | |
| working-directory: ./model_servers/${{ matrix.directory }}/ | |
| if: ${{ matrix.no_gpu }} | |
| run: make test REGISTRY=${{ env.REGISTRY }} IMAGE_NAME=${{ env.REGISTRY_ORG }}/${{ matrix.image_name}}:latest | |
| - name: Login to Container Registry | |
| if: github.event_name == 'push' && github.ref == 'refs/heads/main' | |
| uses: redhat-actions/[email protected] | |
| with: | |
| registry: ${{ env.REGISTRY }} | |
| username: ${{ github.actor }} | |
| password: ${{ secrets.GITHUB_TOKEN }} | |
| - name: Push image | |
| if: github.event_name == 'push' && github.ref == 'refs/heads/main' | |
| uses: redhat-actions/[email protected] | |
| with: | |
| image: ${{ steps.build_image.outputs.image }} | |
| tags: ${{ steps.build_image.outputs.tags }} | |
| registry: ${{ env.REGISTRY }} |