name: xpu-max1100

on:
  workflow_dispatch:
  schedule:
    - cron: "0 0 * * *"
  pull_request:
    paths:
      - ".github/workflows/xpu-max1100.yml"
      - "accelerator/xpu_accelerator.py"
      - "accelerator/abstract_accelerator.py"
      - "accelerator/cpu_accelerator.py"
      - "accelerator/real_accelerator.py"
      - "csrc/xpu/**"
      - "deepspeed/runtime/engine.py"
      - "deepspeed/runtime/bf16_optimizer.py"
      - "deepspeed/runtime/zero/stage_1_and_2.py"
      - "deepspeed/runtime/zero/stage3.py"
      - "deepspeed/runtime/zero/partition_parameters.py"
      - "deepspeed/runtime/zero/partitioned_param_coordinator.py"
      - "deepspeed/runtime/zero/parameter_offload.py"
      - "deepspeed/runtime/pipe/engine.py"
      - "deepspeed/runtime/utils.py"
      - "op_builder/xpu/**"

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

permissions:
  contents: read
  issues: write


jobs:
  unit-tests:
    name: xpu-max1100 / unit tests
    runs-on: [self-hosted, intel, xpu]
    container:
      image: intel/oneapi-basekit:2025.0.2-0-devel-ubuntu22.04
      ports:
        - 80
      options: --privileged -it --rm --device /dev/dri:/dev/dri -v /dev/dri/by-path:/dev/dri/by-path --ipc=host --cap-add=ALL

    steps:
    - uses: actions/checkout@v4
    - name: Install prerequisite
      shell: bash
      run: |
        apt-get update
        apt-get install -y python3.11 python3.11-dev python3-pip clinfo libaio-dev
        pip install --upgrade pip
        pip install py-cpuinfo
        pip install torch==2.10.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/xpu
        pip install .[dev,autotuning]

    - name: Check container state
      shell: bash
      run: |
        ldd --version
        ds_report
        python3 -c "import torch; print('torch:', torch.__version__, torch)"
        python3 -c "import torch; print('XPU available:', torch.xpu.is_available())"
        python3 -c "from deepspeed.accelerator import get_accelerator; print('accelerator:', get_accelerator()._name)"
        pip list

    - name: Unit tests
      shell: bash
      run: |
        cd tests/unit
        export FI_PROVIDER="tcp"
        export I_MPI_SHM=off
        pytest --verbose accelerator/*
        pytest --verbose autotuning/*
        pytest --verbose model_parallelism/*
        pytest --verbose monitor/*
        pytest --verbose utils/*
        pytest --verbose runtime/test_ds_config_model.py
        pytest --verbose runtime/pipe/test_pipe_schedule.py
        pytest --verbose runtime/zero/test_zero_config.py
        pytest --verbose runtime/zero/test_zero_tiled.py
        pytest --verbose runtime/zero/test_zeropp.py
        pytest --verbose runtime/test_autocast.py
        pytest --verbose runtime/test_data.py
        pytest --verbose runtime/zero/test_zero_dynamic_class.py