axolotl/.github/workflows/base.yml

name: ci-cd-base

on:
  push:
    branches:
      - "main"
    paths:
      - 'docker/Dockerfile-base'
      - 'docker/Dockerfile-uv-base'
      - '.github/workflows/base.yml'
  pull_request:
    paths:
      - 'docker/Dockerfile-base'
      - 'docker/Dockerfile-uv-base'
      - '.github/workflows/base.yml'
  workflow_dispatch:

jobs:
  build-base:
    if: github.repository_owner == 'axolotl-ai-cloud'
    timeout-minutes: 480
    # this job needs to be run on self-hosted GPU runners...
    runs-on: ubuntu-latest-m
    strategy:
      fail-fast: false
      matrix:
        include:
          - 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"
            dockerfile: "Dockerfile-base"
          - cuda: "124"
            cuda_version: 12.4.1
            cudnn_version: ""
            python_version: "3.11"
            pytorch: 2.6.0
            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
            dockerfile: "Dockerfile-base"
          - cuda: "126"
            cuda_version: 12.6.3
            cudnn_version: ""
            python_version: "3.11"
            pytorch: 2.6.0
            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
            dockerfile: "Dockerfile-base"
          - cuda: "126"
            cuda_version: 12.6.3
            cudnn_version: ""
            python_version: "3.11"
            pytorch: 2.7.1
            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
            dockerfile: "Dockerfile-base"
          - cuda: "128"
            cuda_version: 12.6.3
            cudnn_version: ""
            python_version: "3.11"
            pytorch: 2.7.1
            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
            dockerfile: "Dockerfile-base"
          - cuda: "128"
            cuda_version: 12.8.1
            cudnn_version: ""
            python_version: "3.11"
            pytorch: nightly
            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
            dockerfile: "Dockerfile-base-nightly"
#          # "next" is for release candidates of pytorch
#          - cuda: "128"
#            cuda_version: 12.8.1
#            cudnn_version: ""
#            python_version: "3.11"
#            pytorch: next
#            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
#            dockerfile: "Dockerfile-base-next"
    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: ${{ secrets.DOCKERHUB_TOKEN }}
      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3
      - name: Build
        uses: docker/build-push-action@v4
        with:
          context: .
          file: ./docker/${{ matrix.dockerfile }}
          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 }}
  build-base-uv:
    if: github.repository_owner == 'axolotl-ai-cloud'
    timeout-minutes: 480
    runs-on: ubuntu-latest-m
    strategy:
      fail-fast: false
      matrix:
        include:
          - cuda: "126"
            cuda_version: 12.6.3
            cudnn_version: ""
            python_version: "3.11"
            pytorch: 2.6.0
            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
            dockerfile: "Dockerfile-uv-base"
          - cuda: "128"
            cuda_version: 12.8.1
            cudnn_version: ""
            python_version: "3.11"
            pytorch: 2.7.1
            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
            dockerfile: "Dockerfile-uv-base"
    steps:
      - name: Checkout
        uses: actions/checkout@v4
      - name: Docker metadata
        id: metadata
        uses: docker/metadata-action@v5
        with:
          images: |
            axolotlai/axolotl-base-uv
      - name: Login to Docker Hub
        uses: docker/login-action@v2
        with:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}
      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3
      - name: Build
        uses: docker/build-push-action@v4
        with:
          context: .
          file: ./docker/${{ matrix.dockerfile }}
          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 }}