build_and_test.yml

name: Build and test
on:
  pull_request:
    branches:
      - master
      - r[0-9]+.[0-9]+
    paths-ignore:
      - 'experimental/torch_xla2/**'
  push:
    branches:
      - master
      - r[0-9]+.[0-9]+
    paths-ignore:
      - 'experimental/torch_xla2/**'
  workflow_dispatch:

concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}-${{ github.event_name == 'workflow_dispatch' }}-${{ github.event_name == 'schedule' }}
  cancel-in-progress: true

jobs:
  # Old CI workflow
  build:
    name: "Build upstream CI image"
    uses: ./.github/workflows/_build.yml
    with:
      ecr-docker-image-base: 308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/xla_base
      gcr-docker-image: gcr.io/tpu-pytorch/xla_base:dev-3.8_cuda_12.1
      cuda: 1
    secrets:
      gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }}

  # New CI workflow
  build-torch-xla:
    name: "Build PyTorch/XLA"
    uses: ./.github/workflows/_build_torch_xla.yml
    with:
      dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_tpuvm
    secrets:
      gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }}

  build-cuda-plugin:
    name: "Build XLA CUDA plugin"
    uses: ./.github/workflows/_build_plugin.yml
    with:
      dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1
    secrets:
      gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }}

  test-python-cpu:
    name: "CPU tests"
    uses: ./.github/workflows/_test.yml
    needs: build-torch-xla
    with:
      dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_tpuvm
      timeout-minutes: 120
      collect-coverage: false
    secrets:
      gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }}

  test-cuda:
    name: "GPU tests"
    uses: ./.github/workflows/_test.yml
    needs: [build-torch-xla, build-cuda-plugin]
    with:
      dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1
      runner: linux.8xlarge.nvidia.gpu
      timeout-minutes: 300
      collect-coverage: false
      install-cuda-plugin: true
    secrets:
      gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }}

  test-tpu:
    name: "TPU tests"
    uses: ./.github/workflows/_tpu_ci.yml
    needs: build-torch-xla
    # Only run this for HEAD and releases
    if: github.event_name == 'push' || contains(github.event.pull_request.labels.*.name, 'tpuci')

  push-docs:
    name: "Build docs"
    uses: ./.github/workflows/_docs.yml
    needs: build-torch-xla
    with:
      dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_tpuvm
    secrets:
      torchxla-bot-token: ${{ secrets.TORCH_XLA_BOT_TOKEN }}