unit_tests.yaml

name: unit-tests
on:
  push:
    branches:
      - "develop"
      - "main"
    paths-ignore:
      - "cmds/**"
      - "**.md"
  pull_request:
    branches:
      - "develop"
      - "main"
    paths-ignore:
      - "cmds/**"
      - "**.md"
env:
  WORKSPACE_PREFIX: $(echo $GITHUB_WORKSPACE |cut -d '/' -f 1-4)
  SLURM_PARTITION: llm_s

jobs:
  check-requirements:
    runs-on: [t_cluster]
    steps:
    - name: mask env
      run: |
        echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
    - uses: actions/checkout@v3
      with:
         fetch-depth: 2
    - name: check-requirements
      run: |
        changed_files=$(git diff --name-only -r HEAD^1 HEAD)
        echo $changed_files
        if [[ $changed_files =~ "runtime.txt" ]]; then
          pip install -r requirements/runtime.txt
        fi

        if [[ $changed_files =~ "torch.txt"  ]]; then
          pip install -r requirements/torch.txt
        fi


  unit_tests_core_pipeline:
    if: ${{ !cancelled() }}
    needs: check-requirements
    runs-on: [t_cluster]
    timeout-minutes: 20
    steps:
    - name: mask env
      run: |
        echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
    - uses: actions/checkout@v3

    - name: core_pipeline
      run: |
        source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
        export PYTHONPATH=$PWD:$PYTHONPATH
        srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:8 python -m pytest -s -v ./tests/test_core/test_pipeline.py

  unit_tests_utils_storage_manager:
    if: ${{ !cancelled() }}
    needs: check-requirements
    runs-on: [t_cluster]
    timeout-minutes: 20
    steps:
    - name: mask env
      run: |
        echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
    - uses: actions/checkout@v3

    - name: utils_storage_manager
      run: |
        source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
        export PYTHONPATH=$PWD:$PYTHONPATH
        srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:8 python -m pytest -s -v ./tests/test_utils/test_storage_manager.py

  unit_tests_model_fused_precision:
    if: ${{ !cancelled() }}
    needs: check-requirements
    runs-on: [t_cluster]
    timeout-minutes: 5
    steps:
    - name: mask env
      run: |
        echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
    - uses: actions/checkout@v3

    - name: model_fused_precision
      run: |
        source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
        export PYTHONPATH=$PWD:$PYTHONPATH
        srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:8 python -m pytest -s -v ./tests/test_model/test_fused_precision/test_fused_precision.py

  unit_tests_data_batch_sampler:
    if: ${{ !cancelled() }}
    needs: check-requirements
    runs-on: [t_cluster]
    timeout-minutes: 10
    steps:
    - name: mask env
      run: |
        echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
    - uses: actions/checkout@v3

    - name: data_batch_sample
      run: |
        source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
        export PYTHONPATH=$PWD:$PYTHONPATH
        srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:8 python -m pytest -s -v ./tests/test_data/test_batch_sampler.py

  unit_tests_utils_timeout:
    if: ${{ !cancelled() }}
    needs: check-requirements
    runs-on: [t_cluster]
    timeout-minutes: 5
    steps:
    - name: mask env
      run: |
        echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
    - uses: actions/checkout@v3

    - name: utils_timeout
      run: |
        source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
        export PYTHONPATH=$PWD:$PYTHONPATH
        srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:1 python -m pytest -s -v ./tests/test_utils/test_timeout.py

  unit_tests_utils_model_checkpoint:
    if: ${{ !cancelled() }}
    needs: check-requirements
    runs-on: [t_cluster]
    timeout-minutes: 5
    steps:
    - name: mask env
      run: |
        echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
    - uses: actions/checkout@v3

    - name: utils_model_checkpoint
      run: |
        source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
        export PYTHONPATH=$PWD:$PYTHONPATH
        srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:2 python -m pytest -s -v  ./tests/test_utils/test_model_checkpoint.py