Switch amd-ci to use MI300X runner. #23
Workflow file for this run
This file contains 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: GitHub Actions CI (AMD) | |
| on: | |
| push: | |
| branches: | |
| - main | |
| paths: | |
| - "src/**" | |
| - "test/**" | |
| pull_request: | |
| branches: | |
| - main | |
| # paths: | |
| # - "src/**" | |
| # - "test/**" | |
| concurrency: | |
| # This causes it to cancel previous in-progress actions on the same PR / branch, | |
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| checkstyle: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v3 | |
| - name: Set up Python | |
| uses: actions/setup-python@v3 | |
| with: | |
| python-version: '3.10' | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install flake8 isort black | |
| - name: Run checkstyle | |
| run: make checkstyle | |
| tests: | |
| runs-on: linux-mi300-gpu-1 | |
| needs: [checkstyle] | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v3 | |
| - name: Set up Python | |
| uses: actions/setup-python@v3 | |
| with: | |
| python-version: '3.10' | |
| - name: Check Docker Version | |
| run: docker version | |
| - name: Check System Environment | |
| run: | | |
| sudo apt list | grep hip | |
| sudo apt list | grep rocm | |
| - name: Check Python Environment | |
| run: | | |
| python3 -m pip list | |
| # - name: Setup Dependencies | |
| # run: | | |
| # python3 -m pip uninstall -y torch torchvision | |
| # python3 -m pip install --pre \ | |
| # torch==2.6.0.dev20241113+rocm6.2 \ | |
| # 'setuptools-scm>=8' \ | |
| # torchvision==0.20.0.dev20241113+rocm6.2 \ | |
| # --extra-index-url https://download.pytorch.org/whl/nightly/rocm6.2 | |
| # python3 -m pip install triton==3.1.0 transformers==4.46.3 | |
| # python3 -m pip install -e .[dev] | |
| # - name: Run Unit Tests | |
| # run: | | |
| # python3 -m pip list | grep torch | |
| # make test | |
| # make test-convergence | |
| # - name: Build Liger-Kernel CI Docker image | |
| # run: sudo docker build -t liger-kernel-ci -f Dockerfile.rocm . | |
| # - name: Run the tests | |
| # run: | | |
| # sudo docker run \ | |
| # --network=host \ | |
| # --group-add=video \ | |
| # --ipc=host \ | |
| # --cap-add=SYS_PTRACE \ | |
| # --security-opt seccomp=unconfined \ | |
| # --device /dev/kfd \ | |
| # --device /dev/dri \ | |
| # liger-kernel-ci \ | |
| # /bin/bash -c "make test; make test-convergence" |