TheRock/compiler/hipify/.github/workflows/test_pytorch_wheels.yml

name: Test PyTorch Wheels

on:
  workflow_dispatch:
    inputs:
      amdgpu_family:
        description: GPU family to test
        required: true
        type: string
        default: "gfx94X-dcgpu"
      test_runs_on:
        description: Runner label to use. The selected runner should have a GPU supported by amdgpu_family
        required: true
        type: string
        default: "linux-mi325-1gpu-ossci-rocm-frac"
      package_index_url:
        description: Base Python package index URL to test, typically nightly/dev URL with a "v2" or "v2-staging" subdir (without a GPU family subdir)
        required: true
        type: string
        default: "https://rocm.nightlies.amd.com/v2"
      python_version:
        required: true
        type: string
        default: "3.12"
      torch_version:
        description: torch package version to install. (e.g. "2.7.1+rocm7.10.0a20251120")
        required: true
        type: string
      pytorch_git_ref:
        description: PyTorch ref to checkout test sources from. (e.g. "nightly", or "release/2.7")
        type: string
        default: "release/2.7"

  workflow_call:
    inputs:
      amdgpu_family:
        required: true
        type: string
      test_runs_on:
        required: true
        type: string
      package_index_url:
        required: true
        type: string
      python_version:
        required: true
        type: string
      torch_version:
        required: true
        type: string
      pytorch_git_ref:
        type: string
        default: "release/2.7"
      repository:
        description: "Repository to checkout. Otherwise, defaults to `github.repository`."
        type: string
      ref:
        description: "Branch, tag or SHA to checkout. Defaults to the reference or SHA that triggered the workflow."
        type: string

permissions:
  contents: read

run-name: Test PyTorch (${{ inputs.amdgpu_family }}, ${{ inputs.torch_version}}, ${{ inputs.test_runs_on }})

jobs:
  test_wheels:
    name: Test PyTorch | ${{ inputs.amdgpu_family }}
    runs-on: ${{ inputs.test_runs_on }}
    container:
      image: ${{ contains(inputs.test_runs_on, 'linux') && 'ghcr.io/rocm/no_rocm_image_ubuntu24_04@sha256:405945a40deaff9db90b9839c0f41d4cba4a383c1a7459b28627047bf6302a26' || null }}
      options: --ipc host
        --group-add video
        --device /dev/kfd
        --device /dev/dri
        --group-add 110
        --env-file /etc/podinfo/gha-gpu-isolation-settings
        --user 0:0 # Running as root, by recommendation of GitHub: https://docs.github.com/en/actions/reference/workflows-and-actions/dockerfile-support#user
    defaults:
      run:
        shell: bash
    env:
      VENV_DIR: ${{ github.workspace }}/.venv
      AMDGPU_FAMILY: ${{ inputs.amdgpu_family }}

    steps:
      - name: Checkout
        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
        with:
          repository: ${{ inputs.repository || github.repository }}
          ref: ${{ inputs.ref || '' }}

      - name: Set up Python
        uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
        with:
          python-version: ${{ inputs.python_version }}

      # TODO: also upload and reference test report together with this logging?
      - name: Summarize workflow inputs
        run: |
          python build_tools/github_actions/summarize_test_pytorch_workflow.py \
            --torch-version=${{ inputs.torch_version }} \
            --pytorch-git-ref=${{ inputs.pytorch_git_ref }} \
            --index-url=${{ inputs.package_index_url }} \
            --index-subdir=${{ inputs.amdgpu_family }}

      - name: Set git options
        run: |
          git config --global core.longpaths true

      # Here we checkout the same version of PyTorch that wheels were built from
      # so we have the right set of test source files. We _probably_ don't need
      # to run HIPIFY or apply any patches, so we skip those steps to save time.
      - name: Checkout PyTorch Source Repos from nightly branch
        if: ${{ (inputs.pytorch_git_ref == 'nightly') }}
        run: |
          python external-builds/pytorch/pytorch_torch_repo.py checkout \
            --gitrepo-origin https://github.com/pytorch/pytorch.git \
            --repo-hashtag nightly \
            --no-hipify --no-patch

      - name: Checkout PyTorch Source Repos from stable branch
        if: ${{ (inputs.pytorch_git_ref != 'nightly') }}
        run: |
          python external-builds/pytorch/pytorch_torch_repo.py checkout \
            --gitrepo-origin https://github.com/ROCm/pytorch.git \
            --repo-hashtag ${{ inputs.pytorch_git_ref }} \
            --no-hipify --no-patch

      - name: Set up virtual environment
        run: |
          python build_tools/setup_venv.py ${VENV_DIR} \
            --packages torch==${{ inputs.torch_version }} \
            --index-url=${{ inputs.package_index_url }} \
            --index-subdir=${{ inputs.amdgpu_family }} \
            --activate-in-future-github-actions-steps

      - name: Install test requirements
        run: |
          python -m pip install -r external-builds/pytorch/requirements-test.txt
          pip freeze

      - name: Run rocm-sdk sanity tests
        run: |
          rocm-sdk test

      - name: Run PyTorch smoketests
        run: |
          python ./external-builds/pytorch/run_pytorch_smoke_tests.py -- \
            --log-cli-level=INFO \
            -v

      - name: (Linux) Run PyTorch tests
        if: ${{ runner.os == 'Linux' }}
        run: |
          python ./external-builds/pytorch/run_pytorch_tests.py -- \
            --continue-on-collection-errors \
            --import-mode=importlib \
            -v

      # Windows testing is a recent addition and is being enabled incrementally.
      # See https://github.com/ROCm/TheRock/issues/2258.
      #
      # Many tests are failing on torch 2.10+ so we limit testing to 2.9.
      # (Obviously that's not ideal, but we need to start somewhere)
      #
      # HACK: The test process does not terminate on its own gracefully,
      # so we write to run_pytorch_tests_exit_code.txt and then kill the process.
      # After killing the process we read the return code to signal it normally.
      # See https://github.com/ROCm/TheRock/issues/999.
      - name: (Windows) Run PyTorch tests
        if: ${{ runner.os == 'Windows' && contains(inputs.torch_version, '2.9') }}
        continue-on-error: true
        run: |
          python ./external-builds/pytorch/run_pytorch_tests.py -- \
            --continue-on-collection-errors \
            --import-mode=importlib \
            -v

      - name: (Windows) Read and propagate exit code
        if: ${{ runner.os == 'Windows' && contains(inputs.torch_version, '2.9') }}
        run: |
          if [ -f run_pytorch_tests_exit_code.txt ]; then
            EXIT_CODE=$(cat run_pytorch_tests_exit_code.txt)
            echo "Exit code from file: ${EXIT_CODE}"
            exit ${EXIT_CODE}
          else
            echo "No run_pytorch_tests_exit_code.txt found"
            exit 1
          fi