model_jobs.yml

name: model jobs

on:
  workflow_call:
    inputs:
      folder_slices:
        required: true
        type: string
      machine_type:
        required: true
        type: string
      slice_id:
        required: true
        type: number
      runner:
        required: true
        type: string
      docker:
        required: true
        type: string

env:
  HF_HOME: /mnt/cache
  TRANSFORMERS_IS_CI: yes
  OMP_NUM_THREADS: 8
  MKL_NUM_THREADS: 8
  RUN_SLOW: yes
  # For gated repositories, we still need to agree to share information on the Hub repo. page in order to get access.
  # This token is created under the bot `hf-transformers-bot`.
  HF_HUB_READ_TOKEN: ${{ secrets.HF_HUB_READ_TOKEN }}
  SIGOPT_API_TOKEN: ${{ secrets.SIGOPT_API_TOKEN }}
  TF_FORCE_GPU_ALLOW_GROWTH: true
  RUN_PT_TF_CROSS_TESTS: 1
  CUDA_VISIBLE_DEVICES: 0,1

jobs:
  run_models_gpu:
    name: " "
    strategy:
      max-parallel: 8
      fail-fast: false
      matrix:
        folders: ${{ fromJson(inputs.folder_slices)[inputs.slice_id] }}
    runs-on:
      group: '${{ inputs.machine_type }}'
    container:
      image: ${{ inputs.docker }}
      options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
    steps:
      - name: Echo input and matrix info
        shell: bash
        run: |
          echo "${{ inputs.folder_slices }}"
          echo "${{ matrix.folders }}"
          echo "${{ toJson(fromJson(inputs.folder_slices)[inputs.slice_id]) }}"

      - name: Echo folder ${{ matrix.folders }}
        shell: bash
        # For folders like `models/bert`, set an env. var. (`matrix_folders`) to `models_bert`, which will be used to
        # set the artifact folder names (because the character `/` is not allowed).
        run: |
          echo "${{ matrix.folders }}"
          matrix_folders=${{ matrix.folders }}
          matrix_folders=${matrix_folders/'models/'/'models_'}
          echo "$matrix_folders"
          echo "matrix_folders=$matrix_folders" >> $GITHUB_ENV

      - 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: Update / Install some packages (for Past CI)
        if: ${{ contains(inputs.docker, '-past-') }}
        working-directory: /transformers
        run: |
          python3 -m pip install -U datasets

      - name: Update / Install some packages (for Past CI)
        if: ${{ contains(inputs.docker, '-past-') && contains(inputs.docker, '-pytorch-') }}
        working-directory: /transformers
        run: |
          python3 -m pip install --no-cache-dir git+https://github.com/huggingface/accelerate@main#egg=accelerate

      - name: NVIDIA-SMI
        run: |
          nvidia-smi

      - name: Environment
        working-directory: /transformers
        run: |
          python3 utils/print_env.py

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

      - name: Set `machine_type` for report and artifact names
        working-directory: /transformers
        shell: bash
        run: |
          echo "${{ inputs.machine_type }}"

          if [ "${{ inputs.machine_type }}" = "aws-g4dn-2xlarge-cache" ]; then
            machine_type=single-gpu
          elif [ "${{ inputs.machine_type }}" = "aws-g4dn-12xlarge-cache" ]; then
            machine_type=multi-gpu
          else
            machine_type=${{ inputs.machine_type }}
          fi

          echo "$machine_type"
          echo "machine_type=$machine_type" >> $GITHUB_ENV

      - name: Run all tests on GPU
        working-directory: /transformers
        run: python3 -m pytest -rsfE -v --make-reports=${{ env.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports tests/${{ matrix.folders }}

      - name: Failure short reports
        if: ${{ failure() }}
        continue-on-error: true
        run: cat /transformers/reports/${{ env.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports/failures_short.txt

      - name: Run test
        shell: bash
        run: |
          mkdir -p /transformers/reports/${{ env.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports
          echo "hello" > /transformers/reports/${{ env.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports/hello.txt
          echo "${{ env.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports"

      - name: "Test suite reports artifacts: ${{ env.machine_type }}_run_models_gpu_${{ env.matrix_folders }}_test_reports"
        if: ${{ always() }}
        uses: actions/upload-artifact@v4
        with:
          name: ${{ env.machine_type }}_run_models_gpu_${{ env.matrix_folders }}_test_reports
          path: /transformers/reports/${{ env.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports