OpenCompass/.github/workflows/daily-run-test.yml

name: daily_run_test

on:
  workflow_dispatch:
  schedule:
    - cron:  '56 16 * * *'

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

env:
  CONDA_ENV: opencompass_regression
  PIP_CACHE_PATH: /cpfs01/user/qa-llm-cicd/.cache/pip
  USERSPACE_PREFIX: /cpfs01/user/qa-llm-cicd
  HF_CACHE_PATH: /cpfs01/shared/public/public_hdd/llmeval/model_weights/hf_hub
  DATEASET_CACHE_PATH: /cpfs01/shared/public/public_hdd/llmeval/llm-evaluation-datasets
  HF_DATASETS_OFFLINE: 1
  TRANSFORMERS_OFFLINE: 1
  HF_HUB_OFFLINE: 1
  TRITON_PTXAS_PATH: /usr/local/cuda/bin/ptxas

jobs:
  build-pypi:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v2
      - name: Set up Python 3.7
        uses: actions/setup-python@v1
        with:
          python-version: 3.7
      - name: Build lagent
        run: |
          pip install wheel
          python setup.py sdist bdist_wheel          
      - name: Upload Artifacts
        uses: actions/upload-artifact@v4
        with:
          if-no-files-found: error
          path: dist/*
          retention-days: 1
          name: my-artifact-${{ github.run_id }}

  daily_run_test:
    needs: build-pypi
    runs-on: self-hosted
    environment: 'prod'
    timeout-minutes: 420 #7hours
    steps:
      - name: Clone repository
        uses: actions/checkout@v2
      - name: Download Artifacts
        uses: actions/download-artifact@v4
        with:
          name: my-artifact-${{ github.run_id }}
      - name: Prepare - create conda env and install torch
        run: |
          . /cpfs01/shared/public/qa-llm-cicd/miniconda3/bin/activate
          conda create -y --name ${{env.CONDA_ENV}} python=3.10
          conda activate ${{env.CONDA_ENV}}
          pip install opencompass*.whl
          pip install /cpfs01/user/qa-llm-cicd/packages/lmdeploy-0.5.0+cu118-cp310-cp310-manylinux2014_x86_64.whl --cache-dir ${{env.PIP_CACHE_PATH}}
          pip install /cpfs01/user/qa-llm-cicd/packages/vllm-0.5.5+cu118-cp310-cp310-manylinux1_x86_64.whl --cache-dir ${{env.PIP_CACHE_PATH}}

          pip install human_eval transformers protobuf pytest gguf msgspec librosa vllm_flash_attn bitsandbytes --cache-dir ${{env.PIP_CACHE_PATH}}
          pip uninstall torch torchvision torchaudio -y
          pip install torch==2.4.0 torchvision==0.19.0 torchaudio==2.4.0 --cache-dir ${{env.PIP_CACHE_PATH}} --index-url https://download.pytorch.org/whl/cu118
          FLASH_ATTENTION_FORCE_BUILD=TRUE pip install /cpfs01/user/qa-llm-cicd/packages/flash_attn-2.6.3+cu118torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
          pip install /cpfs01/user/qa-llm-cicd/packages/xformers-0.0.27.post2+cu118-cp310-cp310-manylinux2014_x86_64.whl --cache-dir ${{env.PIP_CACHE_PATH}}
          conda info --envs
          pip list          
      - name: Prepare - prepare data and hf model
        run: |
          ln -s ${{env.DATEASET_CACHE_PATH}} data
          rm -rf ~/.cache/huggingface/hub -f && mkdir ~/.cache -p && mkdir ~/.cache/huggingface -p
          ln -s ${{env.HF_CACHE_PATH}} ~/.cache/huggingface/hub          
      - name:  Run chat model test
        run: |
          . /cpfs01/shared/public/qa-llm-cicd/miniconda3/bin/activate
          conda activate ${{env.CONDA_ENV}}
          conda info --envs
          sed -i 's/judgemodel/'$(tail -n 1 /cpfs01/shared/public/llmeval/share_info/compassjuder_ip.txt)'/g' .github/scripts/eval_regression_chat.py
          python3 run.py .github/scripts/eval_regression_chat.py --work-dir /cpfs01/user/qa-llm-cicd/report/${{ github.run_id }}/chat --reuse
          rm regression_result_daily -f && ln -s /cpfs01/user/qa-llm-cicd/report/${{ github.run_id }}/chat/*/summary regression_result_daily
          python -m pytest -m chat -s -v --color=yes .github/scripts/oc_score_assert.py          
      - name:  Run base model test
        run: |
          . /cpfs01/shared/public/qa-llm-cicd/miniconda3/bin/activate
          conda activate ${{env.CONDA_ENV}}
          conda info --envs
          python3 run.py .github/scripts/eval_regression_base.py --work-dir /cpfs01/user/qa-llm-cicd/report/${{ github.run_id }}/base --reuse
          rm regression_result_daily -f && ln -s /cpfs01/user/qa-llm-cicd/report/${{ github.run_id }}/base/*/summary regression_result_daily
          python -m pytest -m base -s -v --color=yes .github/scripts/oc_score_assert.py          
      - name:  Run command testcase
        run: |
          . /cpfs01/shared/public/qa-llm-cicd/miniconda3/bin/activate
          conda activate ${{env.CONDA_ENV}}
          conda info --envs
          export from_tf=TRUE
          python tools/list_configs.py internlm2_5 mmlu
          python run.py --models hf_internlm2_5_7b --datasets race_ppl --work-dir /cpfs01/user/qa-llm-cicd/report/${{ github.run_id }}/cmd1 --reuse
          rm regression_result_daily -f && ln -s /cpfs01/user/qa-llm-cicd/report/${{ github.run_id }}/cmd1/*/summary regression_result_daily
          python -m pytest -m case1 -s -v --color=yes .github/scripts/oc_score_assert.py
          python run.py --models hf_internlm2_5_7b_chat --datasets race_gen -a lmdeploy --work-dir /cpfs01/user/qa-llm-cicd/report/${{ github.run_id }}/cmd2 --reuse
          rm regression_result_daily -f && ln -s /cpfs01/user/qa-llm-cicd/report/${{ github.run_id }}/cmd2/*/summary regression_result_daily
          python -m pytest -m case2 -s -v --color=yes .github/scripts/oc_score_assert.py
          python run.py --datasets race_ppl --hf-type base --hf-path internlm/internlm2_5-7b --work-dir /cpfs01/user/qa-llm-cicd/report/${{ github.run_id }}/cmd3 --reuse
          rm regression_result_daily -f && ln -s /cpfs01/user/qa-llm-cicd/report/${{ github.run_id }}/cmd3/*/summary regression_result_daily
          python -m pytest -m case3 -s -v --color=yes .github/scripts/oc_score_assert.py
          python run.py --datasets race_gen --hf-type chat --hf-path internlm/internlm2_5-7b-chat --work-dir /cpfs01/user/qa-llm-cicd/report/${{ github.run_id }}/cmd4 --reuse
          rm regression_result_daily -f && ln -s /cpfs01/user/qa-llm-cicd/report/${{ github.run_id }}/cmd4/*/summary regression_result_daily
          python -m pytest -m case4 -s -v --color=yes .github/scripts/oc_score_assert.py          
      - name:  Remove Conda Env
        if: always()
        run: |
          rm -rf regression_result_daily
          . /cpfs01/shared/public/qa-llm-cicd/miniconda3/bin/activate
          conda env remove -y --name ${{env.CONDA_ENV}}
          conda info --envs          

  notify_to_feishu:
    if: ${{ always() && !cancelled() && contains(needs.*.result, 'failure') && (github.ref_name == 'develop' || github.ref_name == 'main') }}
    needs: [daily_run_test]
    environment: 'prod'
    timeout-minutes: 5
    runs-on: self-hosted
    steps:
      - name: notify
        run: |
          curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"Opencompass- Daily test failed","content":[[{"tag":"text","text":"branch: ${{github.ref_name}}, run action: ${{github.workflow}} failed. "},{"tag":"a","text":"Please click here for details ","href":"https://github.com/'${{ github.repository }}'/actions/runs/'${GITHUB_RUN_ID}'"},{"tag":"at","user_id":"'${{ secrets.USER_ID }}'"}]]}}}}'  ${{ secrets.WEBHOOK_URL }}