axolotl/.github/workflows/tests.yml

name: Tests
on:
  # check on push/merge to main, PRs, and manual triggers
  merge_group:
  push:
    branches:
      - "main"
    paths:
      - '**.py'
      - 'requirements.txt'
      - '.github/workflows/*.yml'
      - 'requirements-tests.txt'
      - 'cicd/cicd.sh'
      - 'cicd/Dockerfile.jinja'
  pull_request:
      types: [opened, synchronize, reopened, ready_for_review]
      paths:
       - '**.py'
       - 'requirements.txt'
       - '.github/workflows/*.yml'
       - 'requirements-tests.txt'
       - 'cicd/cicd.sh'
       - 'cicd/Dockerfile.jinja'
  workflow_dispatch:

# Cancel jobs on the same ref if a new one is triggered
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}

env:
  TRANSFORMERS_IS_CI: "yes"

jobs:
  pre-commit:
    name: pre-commit
    runs-on: ubuntu-latest
    if: ${{ !github.event.pull_request.draft }}
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with:
          python-version: "3.11"
          cache: 'pip' # caching pip dependencies
      - uses: pre-commit/action@v3.0.1
        env:
          SKIP: no-commit-to-branch

  prime-cdn-s3-cache:
    name: Prefetch S3 once to prime the CDN cache
    runs-on: ubuntu-latest
    if: ${{ !github.event.pull_request.draft }}
    timeout-minutes: 10
    steps:
      - name: Restore Cache from S3
        id: hf-cache-restore-s3
        run: |
          curl -L https://axolotl-ci.b-cdn.net/hf-cache.tar.zst > /dev/null

  pytest:
    name: PyTest
    runs-on: ubuntu-latest
    if: ${{ !github.event.pull_request.draft }}
    needs: [prime-cdn-s3-cache]
    strategy:
      fail-fast: false
      matrix:
        python_version: ["3.12"]  # TODO include py3.14 once https://github.com/mistralai/mistral-common/pull/194 is merged
        pytorch_version: ["2.8.0", "2.9.1", "2.10.0"]
#        exclude:
#          - python_version: "3.14"
#            pytorch_version: "2.8.0"
#          - python_version: "3.14"
#            pytorch_version: "2.9.1"
    timeout-minutes: 20

    steps:
      - name: cleanup node
        run: |
          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL

      - name: Check out repository code
        uses: actions/checkout@v4

      - name: Restore Cache from S3
        id: hf-cache-restore-s3
        run: |
          mkdir -p ~/.cache/huggingface/hub
          curl -L https://axolotl-ci.b-cdn.net/hf-cache.tar.zst | tar -xpf - -C ~/.cache/huggingface/hub/  --use-compress-program unzstd --strip-components=1
          ls -ltr ~/.cache/huggingface/hub/

      - name: Setup Python
        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python_version }}
          cache: 'pip' # caching pip dependencies

      - name: upgrade pip
        run: |
          pip3 install --upgrade pip
          pip3 install --upgrade packaging==26.0 setuptools==75.8.0 wheel

      - name: Install PyTorch
        run: |
          pip3 install --no-cache-dir torch==${{ matrix.pytorch_version }} torchvision

      - name: Install dependencies
        run: |
          pip3 show torch
          pip3 install --no-cache-dir --no-build-isolation -U -e .
          python scripts/unsloth_install.py | sh
          python scripts/cutcrossentropy_install.py | sh
          pip3 install -r requirements-dev.txt -r requirements-tests.txt

      - name: cleanup pip cache
        run: |
          find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;

      - name: Make sure PyTorch version wasn't clobbered
        run: |
          python -c "import torch; assert '${{ matrix.pytorch_version }}' in torch.__version__"

      - name: Ensure axolotl CLI was installed
        run: |
          axolotl --help

      - name: Pre-Download dataset fixture
        run: |
          hf download --repo-type=dataset axolotl-ai-internal/axolotl-oss-dataset-fixtures

      - name: Show HF cache
        run: hf cache ls

      - name: Run tests
        run: |
          df -h
          pytest -v --durations=10 -n4 --dist loadfile --ignore=tests/e2e/ --ignore=tests/patched/ --ignore=tests/cli/ --ignore=tests/monkeypatch/ tests/ --cov=axolotl --cov-report=xml
          df -h
          pytest -v --durations=10 tests/monkeypatch/ --cov=axolotl --cov-append --cov-report=xml
          df -h
          pytest -v --durations=10 tests/patched/ --cov=axolotl --cov-append --cov-report=xml
          df -h
          pytest -v --durations=10 tests/cli/ --cov=axolotl --cov-append --cov-report=xml

      - name: Show HF cache
        run: hf cache ls

      - name: Upload coverage to Codecov
        uses: codecov/codecov-action@v5
        with:
          token: ${{ secrets.CODECOV_TOKEN }}
          files: ./coverage.xml
          flags: unittests,pytorch-${{ matrix.pytorch_version }}
          fail_ci_if_error: false

  pytest-sdist:
    name: PyTest from Source Dist
    runs-on: ubuntu-latest
    if: ${{ !github.event.pull_request.draft }}
    needs: [prime-cdn-s3-cache]
    strategy:
      fail-fast: false
      matrix:
        python_version: ["3.12"]  # TODO include py3.14 once https://github.com/mistralai/mistral-common/pull/194 is merged
        pytorch_version: ["2.8.0", "2.9.1", "2.10.0"]
#        exclude:
#          - python_version: "3.14"
#            pytorch_version: "2.8.0"
#          - python_version: "3.14"
#            pytorch_version: "2.9.1"
    timeout-minutes: 30

    steps:
      - name: cleanup node
        run: |
          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL

      - name: Check out repository code
        uses: actions/checkout@v4

      - name: Restore Cache from S3
        id: hf-cache-restore-s3
        run: |
          mkdir -p ~/.cache/huggingface/hub
          curl -L https://axolotl-ci.b-cdn.net/hf-cache.tar.zst | tar -xpf - -C ~/.cache/huggingface/hub/  --use-compress-program unzstd --strip-components=1
          ls -ltr ~/.cache/huggingface/hub/

      - name: Setup Python
        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python_version }}
          cache: 'pip' # caching pip dependencies

      - name: upgrade pip
        run: |
          pip3 install --upgrade pip
          pip3 install --upgrade packaging==26.0 setuptools==75.8.0 setuptools_scm build wheel psutil

      - name: Install PyTorch
        run: |
          pip3 install --no-cache-dir torch==${{ matrix.pytorch_version }} torchvision

      - name: Install dependencies
        run: |
          pip3 show torch
          python -m build --no-isolation --sdist
          pip3 install --no-cache-dir --no-build-isolation dist/axolotl*.tar.gz
          python scripts/unsloth_install.py | sh
          python scripts/cutcrossentropy_install.py | sh
          pip3 install -r requirements-dev.txt -r requirements-tests.txt

      - name: cleanup pip cache
        run: |
          find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;

      - name: Make sure PyTorch version wasn't clobbered
        run: |
          python -c "import torch; assert '${{ matrix.pytorch_version }}' in torch.__version__"

      - name: Ensure axolotl CLI was installed
        run: |
          axolotl --help

      - name: Show HF cache
        run: hf cache ls

      - name: Run tests
        run: |
          pytest -v --durations=10 -n4 --dist loadfile --ignore=tests/e2e/ --ignore=tests/patched/ --ignore=tests/cli/ --ignore=tests/monkeypatch/ tests/ --cov=axolotl --cov-report=xml
          pytest -v --durations=10 tests/monkeypatch/ --cov=axolotl --cov-append --cov-report=xml
          pytest -v --durations=10 tests/cli/

      - name: Show HF cache
        run: hf cache ls

  gate-skip-e2e:
    needs: [pre-commit]
    runs-on: ubuntu-latest
    outputs:
      skip: ${{ steps.compute.outputs.skip }}
    steps:
      - uses: actions/github-script@v7
        id: compute
        with:
          script: |
            const token = /\[skip-e2e\]/i;
            let msg = '';
            if (context.eventName === 'push') {
              msg = context.payload.head_commit?.message || '';
            } else if (context.eventName === 'pull_request') {
              const { owner, repo } = context.repo;
              const prNumber = context.payload.pull_request.number;
              const commits = await github.paginate(
                github.rest.pulls.listCommits,
                { owner, repo, pull_number: prNumber, per_page: 100 }
              );
              msg = commits.at(-1)?.commit?.message || '';
            }
            const title = context.payload.pull_request?.title || '';
            const body  = context.payload.pull_request?.body  || '';
            const skip = token.test(msg) || token.test(title) || token.test(body);
            core.setOutput('skip', String(skip));

  docker-e2e-tests-1st:
    # Run this job first as a gate for running the remainder of the test matrix
    if: >
      github.repository_owner == 'axolotl-ai-cloud' &&
      (github.event_name != 'pull_request' || !github.event.pull_request.draft) &&
      needs.gate-skip-e2e.outputs.skip != 'true'
    # this job needs to be run on self-hosted GPU runners...
    runs-on: [self-hosted, modal]
    timeout-minutes: 120
    needs: [pre-commit, pytest]

    strategy:
      fail-fast: false
      matrix:
        include:
          - cuda: 130
            cuda_version: 13.0.0
            python_version: "3.12"
            pytorch: 2.9.1
            num_gpus: 1
            axolotl_extras:
            dockerfile: "Dockerfile-uv.jinja"
    steps:
      - name: Checkout
        uses: actions/checkout@v4
      - name: Install Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"
      - name: Install Modal
        run: |
          python -m pip install --upgrade pip
          pip install modal==1.3.0.post1 jinja2
      - name: Update env vars
        run: |
          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
          echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
          echo "MODAL_IMAGE_BUILDER_VERSION=2024.10" >> $GITHUB_ENV
          echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
          echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV
          echo "E2E_DOCKERFILE=${{ matrix.dockerfile || 'Dockerfile.jinja'}}" >> $GITHUB_ENV
      - name: Run tests job on Modal
        run: |
          modal run cicd.e2e_tests

  docker-e2e-tests:
    if: >
      github.repository_owner == 'axolotl-ai-cloud' &&
      (github.event_name != 'pull_request' || !github.event.pull_request.draft) &&
      needs.gate-skip-e2e.outputs.skip != 'true'
    # this job needs to be run on self-hosted GPU runners...
    runs-on: [self-hosted, modal]
    timeout-minutes: 120
    # Only run the remainder of the matrix if the first e2e check passed;
    # this is to save on wasted compute costs for known failures that get caught in the first run
    needs: [pre-commit, pytest, gate-skip-e2e, docker-e2e-tests-1st]

    strategy:
      fail-fast: false
      matrix:
        include:
          - cuda: 128
            cuda_version: 12.8.1
            python_version: "3.11"
            pytorch: 2.8.0
            num_gpus: 1
            gpu_type: "B200"
            axolotl_extras: fbgemm-gpu
          - cuda: 128
            cuda_version: 12.8.1
            python_version: "3.11"
            pytorch: 2.9.1
            num_gpus: 1
            axolotl_extras:
          - cuda: 128
            cuda_version: 12.8.1
            python_version: "3.11"
            pytorch: 2.10.0
            num_gpus: 1
            axolotl_extras:
          - cuda: 130
            cuda_version: 13.0.0
            python_version: "3.11"
            pytorch: 2.9.1
            num_gpus: 1
            axolotl_extras:
    steps:
      - name: Checkout
        uses: actions/checkout@v4
      - name: Install Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"
      - name: Install Modal
        run: |
          python -m pip install --upgrade pip
          pip install modal==1.3.0.post1 jinja2
      - name: Update env vars
        run: |
          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
          echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
          echo "MODAL_IMAGE_BUILDER_VERSION=2024.10" >> $GITHUB_ENV
          echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
          echo "GPU_TYPE=${{ matrix.gpu_type || 'L40S'}}" >> $GITHUB_ENV
          echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV
          echo "E2E_DOCKERFILE=${{ matrix.dockerfile || 'Dockerfile.jinja'}}" >> $GITHUB_ENV
      - name: Run tests job on Modal
        run: |
          modal run cicd.e2e_tests

  docker-e2e-cleanup:
    runs-on: [self-hosted, modal]
    timeout-minutes: 90
    needs: [docker-e2e-tests]
    if: ${{ !github.event.pull_request.draft }}

    strategy:
      fail-fast: false
      matrix:
        include:
          - cuda: 128
            cuda_version: 12.8.1
            python_version: "3.11"
            pytorch: 2.9.1
            num_gpus: 1
            axolotl_extras:
    steps:
      - name: Checkout
        uses: actions/checkout@v4
      - name: Install Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"
      - name: Install Modal
        run: |
          python -m pip install --upgrade pip
          pip install modal==1.3.0.post1 jinja2
      - name: Update env vars
        run: |
          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
          echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
          echo "MODAL_IMAGE_BUILDER_VERSION=2024.10" >> $GITHUB_ENV
          echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
          echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV
      - name: Run tests job on Modal
        run: |
          modal run cicd.cleanup