Catchall PR for all 355_wip related changes #475
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Aiter Test | |
| on: | |
| push: | |
| branches: [main] | |
| pull_request: | |
| branches: [main] # Triggers on PRs targeting `main` | |
| workflow_dispatch: | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: true | |
| env: | |
| DOCKER_IMAGE: "rocm/pytorch:latest" | |
| jobs: | |
| standard: | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| runner: [aiter-1gpu-runner] # TODO: add mi35x runner | |
| runs-on: ${{ matrix.runner }} | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v4 | |
| - name: Sync submodules | |
| run: | | |
| set -euo pipefail | |
| if [[ ${{ github.ref }} == "refs/heads/main" ]]; then | |
| echo "It's main branch, syncing latest CK..." | |
| git submodule sync | |
| git submodule update --init --recursive --remote --depth 1 --jobs 4 | |
| else | |
| echo "It's a PR branch, syncing specific CK..." | |
| git submodule sync | |
| git submodule update --init --recursive --depth 1 --jobs 4 | |
| fi | |
| - name: Clean up Rocm processes | |
| run: | | |
| ./.github/scripts/clean_up_rocm.sh | |
| - name: Run the container | |
| run: | | |
| set -ex | |
| echo "Starting container: aiter_test" | |
| docker run -dt \ | |
| --device=/dev/dri \ | |
| --device=/dev/kfd \ | |
| --shm-size=16G \ | |
| --group-add $(getent group render | cut -d: -f3) \ | |
| --group-add $(getent group video | cut -d: -f3) \ | |
| -v "${{ github.workspace }}:/workspace" \ | |
| -w /workspace \ | |
| --name aiter_test \ | |
| ${{ env.DOCKER_IMAGE }} | |
| - name: Setup-Triton | |
| run: | | |
| set -ex | |
| echo "Setting up Triton..." | |
| docker exec \ | |
| -w /workspace \ | |
| aiter_test \ | |
| ./.github/scripts/build_triton.sh | |
| - name: Tests | |
| run: | | |
| set -ex | |
| docker exec \ | |
| -w /workspace \ | |
| aiter_test \ | |
| ./.github/scripts/aiter_test.sh | |
| - name: Upload test logs | |
| uses: actions/upload-artifact@v4 | |
| if: always() | |
| with: | |
| name: standard-test-logs | |
| path: latest_test.log | |
| - name: Cleanup container | |
| if: always() | |
| run: | | |
| docker rm -f aiter_test || true | |
| - name: Clean up Rocm processes | |
| if: always() | |
| run: | | |
| ./.github/scripts/clean_up_rocm.sh | |
| multi-gpu: | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| runner: [aiter-8gpu-runner] # TODO: add mi35x runner | |
| runs-on: ${{ matrix.runner }} | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v4 | |
| - name: Sync submodules | |
| run: | | |
| set -euo pipefail | |
| if [[ ${{ github.ref }} == "refs/heads/main" ]]; then | |
| echo "It's main branch, syncing latest CK..." | |
| git submodule sync | |
| git submodule update --init --recursive --remote --depth 1 --jobs 4 | |
| else | |
| echo "It's a PR branch, syncing specific CK..." | |
| git submodule sync | |
| git submodule update --init --recursive --depth 1 --jobs 4 | |
| fi | |
| - name: Clean up Rocm processes | |
| run: ./.github/scripts/clean_up_rocm.sh | |
| - name: Run the container | |
| run: | | |
| set -ex | |
| echo "Starting container: aiter_test" | |
| docker run -dt \ | |
| --device=/dev/dri \ | |
| --device=/dev/kfd \ | |
| --shm-size=16G \ | |
| --group-add $(getent group render | cut -d: -f3) \ | |
| --group-add $(getent group video | cut -d: -f3) \ | |
| -v "${{ github.workspace }}:/workspace" \ | |
| -w /workspace \ | |
| --name aiter_test \ | |
| ${{ env.DOCKER_IMAGE }} | |
| - name: Setup-Triton | |
| run: | | |
| set -ex | |
| echo "Setting up Triton..." | |
| docker exec \ | |
| -w /workspace \ | |
| aiter_test \ | |
| ./.github/scripts/build_triton.sh | |
| - name: Tests | |
| run: | | |
| set -ex | |
| docker exec \ | |
| -e MULTIGPU=TRUE \ | |
| -w /workspace \ | |
| aiter_test \ | |
| ./.github/scripts/aiter_test.sh | |
| - name: Upload test logs | |
| uses: actions/upload-artifact@v4 | |
| if: always() | |
| with: | |
| name: multigpu-test-logs | |
| path: latest_test.log | |
| - name: Cleanup container | |
| if: always() | |
| run: | | |
| docker rm -f aiter_test || true | |
| - name: Clean up Rocm processes | |
| if: always() | |
| run: | | |
| ./.github/scripts/clean_up_rocm.sh |