test_iree.yml

# Copyright 2024 Advanced Micro Devices, Inc.
#
# Licensed under the Apache License v2.0 with LLVM Exceptions.
# See https://llvm.org/LICENSE.txt for license information.
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception

name: IREE Test Suite
on:
  pull_request:
    paths:
      # This file itself.
      - ".github/workflows/test_iree.yml"
      # The iree_tests subproject.
      - "iree_tests/**"
      # The iree_special_models subproject.
      - "iree_special_models/**"
  workflow_dispatch:
  schedule:
    # Runs at 3:00 PM UTC, which is 8:00 AM PST
    - cron: "0 15 * * *"

concurrency:
  # A PR number if a pull request and otherwise the commit hash. This cancels
  # queued and in-progress runs for the same PR (presubmit) or commit
  # (postsubmit). The workflow name is prepended to avoid conflicts between
  # different workflows.
  group: ${{ github.workflow }}-${{ github.event.number || github.sha }}
  cancel-in-progress: true

jobs:
  models:
    name: "Models :: ${{ matrix.name }} :: ${{ matrix.runs-on }}"
    runs-on: ${{ matrix.runs-on }}
    strategy:
      fail-fast: false
      matrix:
        include:
          - name: cpu_llvm_task
            runs-on: nodai-amdgpu-mi250-x86-64
            models-config-file: models_cpu_llvm_task.json
            backend: cpu
          - name: gpu_mi250_rocm
            runs-on: nodai-amdgpu-mi250-x86-64
            models-config-file: models_gpu_rocm_gfx90a.json
            backend: rocm
    env:
      VENV_DIR: ${{ github.workspace }}/.venv
      ROCM_CHIP: gfx90a
      IREE_TEST_FILES: /groups/aig_sharks/iree-tests-cache-nod
      IREE_TEST_PATH_EXTENSION: ${{ github.workspace }}/iree_tests/specs
      MODELS_CONFIG_FILE_PATH: iree_tests/configs/${{ matrix.models-config-file }}
      TEST_SUITE_REPO_ROOT: ${{ github.workspace }}
    steps:
      - name: "Checking out repository"
        uses: actions/checkout@v4
        with:
          submodules: false
          lfs: true

      # Install Python packages.
      # Note: skipping actions/setup-python since these self-hosted runners already have Python.
      - name: "Setup Python venv"
        run: python3 -m venv ${VENV_DIR}
      - name: "Installing IREE nightly release Python packages"
        run: |
          source ${VENV_DIR}/bin/activate
          python3 -m pip install \
            --find-links https://iree.dev/pip-release-links.html \
            --upgrade \
            iree-compiler \
            iree-runtime
      - name: "Installing Python test requirements"
        run: |
          source ${VENV_DIR}/bin/activate
          python3 -m pip install -r iree_tests/requirements.txt
          python3 -m pip install -r iree_special_models/requirements.txt
          pip install --no-compile --pre --upgrade -e common_tools

      # Download remote files.
      - name: "Downloading remote files for real weight model tests"
        run: |
          source ${VENV_DIR}/bin/activate
          python3 iree_tests/download_remote_files.py --root-dir iree_special_models
          python3 iree_tests/download_remote_files.py --root-dir iree_tests/pytorch/models
          python3 iree_tests/download_remote_files.py --root-dir iree_tests/sharktank

      - name: "Running real weight model tests"
        if: "matrix.models-config-file != '' && !cancelled()"
        run: |
          source ${VENV_DIR}/bin/activate
          pytest \
            iree_tests/pytorch/models \
            iree_tests/sharktank \
            -n 4 \
            -rA \
            -k real_weights \
            --no-skip-tests-missing-files \
            --capture=no \
            --log-cli-level=info \
            --timeout=1200 \
            --durations=0 \
            --config-files=${MODELS_CONFIG_FILE_PATH}

      - name: "Running SDXL special model tests"
        id: special_models_sdxl
        if: ${{ !cancelled() }}
        run: |
          source ${VENV_DIR}/bin/activate
          pytest iree_special_models/sdxl \
            -k ${{ matrix.backend }} \
            -rpfE \
            --capture=no \
            --log-cli-level=info \
            --timeout=1200 \
            --durations=0

      - name: "Running SD3 special model tests"
        id: special_models_sd3
        if: ${{ !cancelled() }}
        run: |
          source ${VENV_DIR}/bin/activate
          pytest iree_special_models/sd3 \
            -k ${{ matrix.backend }} \
            -rpfE \
            --capture=no \
            --log-cli-level=info \
            --timeout=1200 \
            --durations=0

      - name: "Running SDXL ROCm pipeline benchmark"
        if: |
          contains(matrix.name, 'rocm') &&
          steps.special_models_sdxl.outcome == 'success'
        run: |
          source ${VENV_DIR}/bin/activate
          pytest iree_tests/benchmarks/sdxl/benchmark_sdxl_rocm.py \
            --goldentime-rocm-e2e-ms 1450.0 \
            --goldentime-rocm-unet-ms 370.0 \
            --goldentime-rocm-clip-ms 18.5 \
            --goldentime-rocm-vae-ms 315.0 \
            --goldendispatch-rocm-unet 1714 \
            --goldendispatch-rocm-clip 1569 \
            --goldendispatch-rocm-vae 248 \
            --goldensize-rocm-unet-bytes 2280000  \
            --goldensize-rocm-clip-bytes 860000 \
            --goldensize-rocm-vae-bytes 840000 \
            --gpu-number 6 \
            --rocm-chip gfx90a \
            --log-cli-level=info
          echo "$(<job_summary.md )" >> $GITHUB_STEP_SUMMARY