[docker] experiment with nvcr pytorch image for torch 2.5.1 #87
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: ci-cd-base | |
| on: | |
| push: | |
| branches: | |
| - "main" | |
| paths: | |
| - 'Dockerfile-base' | |
| - '.github/workflows/base.yml' | |
| pull_request: | |
| paths: | |
| - 'Dockerfile-base' | |
| - '.github/workflows/base.yml' | |
| workflow_dispatch: | |
| jobs: | |
| build-base: | |
| if: github.repository_owner == 'axolotl-ai-cloud' | |
| # this job needs to be run on self-hosted GPU runners... | |
| runs-on: axolotl-gpu-runner | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| include: | |
| # - cuda: "121" | |
| # cuda_version: 12.1.1 | |
| # cudnn_version: 8 | |
| # python_version: "3.10" | |
| # pytorch: 2.3.1 | |
| # torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX" | |
| # from_base_img: "" | |
| # from_base_tag: "" | |
| # - cuda: "121" | |
| # cuda_version: 12.1.1 | |
| # cudnn_version: 8 | |
| # python_version: "3.11" | |
| # pytorch: 2.3.1 | |
| # torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX" | |
| # from_base_img: "" | |
| # from_base_tag: "" | |
| # - cuda: "124" | |
| # cuda_version: 12.4.1 | |
| # cudnn_version: "" | |
| # python_version: "3.11" | |
| # pytorch: 2.4.1 | |
| # torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX" | |
| # from_base_img: "" | |
| # from_base_tag: "" | |
| - cuda: "124" | |
| cuda_version: 12.4.1 | |
| cudnn_version: "" | |
| python_version: "3.11" | |
| pytorch: 2.5.1 | |
| torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX" | |
| from_base_img: nvcr.io/nvidia/pytorch | |
| from_base_tag: 24.10-py3 | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Docker metadata | |
| id: metadata | |
| uses: docker/metadata-action@v5 | |
| with: | |
| images: | | |
| winglian/axolotl-base | |
| # axolotlai/axolotl-base | |
| - name: Login to Docker Hub | |
| uses: docker/login-action@v2 | |
| with: | |
| username: ${{ secrets.DOCKERHUB_USERNAME }} | |
| password: ${{ secrets.DOCKERHUB_TOKEN }} | |
| - name: Set up Docker Buildx | |
| uses: docker/setup-buildx-action@v3 | |
| - name: Build | |
| uses: docker/build-push-action@v4 | |
| with: | |
| context: . | |
| file: ./docker/Dockerfile-base | |
| push: true | |
| # push: ${{ github.event_name != 'pull_request' }} | |
| tags: ${{ steps.metadata.outputs.tags }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }} | |
| labels: ${{ steps.metadata.outputs.labels }} | |
| build-args: | | |
| CUDA_VERSION=${{ matrix.cuda_version }} | |
| CUDNN_VERSION=${{ matrix.cudnn_version }} | |
| CUDA=${{ matrix.cuda }} | |
| PYTHON_VERSION=${{ matrix.python_version }} | |
| PYTORCH_VERSION=${{ matrix.pytorch }} | |
| TORCH_CUDA_ARCH_LIST=${{ matrix.torch_cuda_arch_list }} | |
| BASE_IMAGE=${{ matrix.from_base_img || '' }} | |
| BASE_TAG=${{ matrix.from_base_tag || '' }} |