huawei-ascend-npu.yml

name: huawei-ascend-npu

on:
  workflow_dispatch:
  pull_request:
    paths:
      - '.github/workflows/huawei-ascend-npu.yml'
      - 'requirements/**'
  schedule:
    - cron: "0 0 * * *"
  
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

permissions:
  contents: read
  issues: write

jobs:
  unit-tests:
    runs-on: [self-hosted, ascend, npu]
    container:
      image: ascendai/cann
      ports:
        - 80

    steps:
    - uses: actions/checkout@v4

    - name: Install pytorch 
      run: |
        apt-get update
        pip3 install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu118
        pip3 install torch_npu
        python -c "import torch; print('torch:', torch.__version__, torch)"
        python -c "import torch; import torch_npu; print('torch_npu:', torch.npu.is_available(),',version:', torch_npu.__version__, torch)"

    - name: Install deepspeed
      run: |
        pip install .
        ds_report

    - name: Python environment
      run: |
        pip list

    - name: Multi-card parallel training
      run: |
        git clone https://github.com/microsoft/DeepSpeedExamples.git
        cd DeepSpeedExamples
        deepspeed ./training/cifar/cifar10_deepspeed.py