transformers/.github/workflows/doctests.yml

name: Doctests

on:
  push:
    branches:
      - run_doctest*
  repository_dispatch:
  schedule:
    - cron: "17 2 * * *"

env:
  NUM_SLICES: 3

permissions:
  contents: read

jobs:
  setup:
    name: Setup
    runs-on: 
      group: aws-g5-4xlarge-cache
    container:
      image: huggingface/transformers-all-latest-gpu
      options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
    outputs:
      job_splits: ${{ steps.set-matrix.outputs.job_splits }}
      split_keys: ${{ steps.set-matrix.outputs.split_keys }}
    steps:
      - name: Update clone
        working-directory: /transformers
        run: |
          git fetch && git checkout ${{ github.sha }}

      - name: Reinstall transformers in edit mode (remove the one installed during docker image build)
        working-directory: /transformers
        run: python3 -m pip uninstall -y transformers && python3 -m pip install -e .

      - name: Show installed libraries and their versions
        working-directory: /transformers
        run: pip freeze

      - name: Check values for matrix
        working-directory: /transformers
        run: |
          python3 utils/split_doctest_jobs.py
          python3 utils/split_doctest_jobs.py --only_return_keys --num_splits ${{ env.NUM_SLICES }}

      - id: set-matrix
        working-directory: /transformers
        name: Set values for matrix
        run: |
          echo "job_splits=$(python3 utils/split_doctest_jobs.py)" >> $GITHUB_OUTPUT
          echo "split_keys=$(python3 utils/split_doctest_jobs.py --only_return_keys --num_splits ${{ env.NUM_SLICES }})" >> $GITHUB_OUTPUT

  call_doctest_job:
    name: "Call doctest jobs"
    needs: setup
    strategy:
      max-parallel: 1  # 1 split at a time (in `doctest_job.yml`, we set `8` to run 8 jobs at the same time)
      fail-fast: false
      matrix:
        split_keys: ${{ fromJson(needs.setup.outputs.split_keys) }}
    uses: ./.github/workflows/doctest_job.yml
    with:
      job_splits: ${{ needs.setup.outputs.job_splits }}
      split_keys: ${{ toJson(matrix.split_keys) }}
    secrets: inherit

  send_results:
    name: Send results to webhook
    runs-on: ubuntu-22.04
    if: always()
    needs: [call_doctest_job]
    steps:
      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
        with:
          persist-credentials: false
      - uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
      - name: Send message to Slack
        env:
          CI_SLACK_BOT_TOKEN: ${{ secrets.CI_SLACK_BOT_TOKEN }}
          ACCESS_REPO_INFO_TOKEN: ${{ secrets.ACCESS_REPO_INFO_TOKEN }}
          # Use `CI_SLACK_CHANNEL_DUMMY_TESTS` when doing experimentation
          SLACK_REPORT_CHANNEL: ${{ secrets.CI_SLACK_CHANNEL_ID_DAILY_DOCS }}
        run: |
          pip install slack_sdk
          python utils/notification_service_doc_tests.py

      - name: "Upload results"
        if: ${{ always() }}
        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
        with:
          name: doc_test_results
          path: doc_test_results