nv-sd #5
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: nv-sd | |
| on: | |
| workflow_dispatch: | |
| schedule: | |
| - cron: "0 0 * * 0" | |
| pull_request: | |
| paths: | |
| - "deepspeed/ops/transformer/inference/diffusers_**" | |
| - "tests/unit/inference/test_stable_diffusion.py" | |
| - "deepspeed/model_implementations/diffusers/unet.py" | |
| - "deepspeed/model_implementations/diffusers/vae.py" | |
| - "deepspeed/module_inject/containers/vae.py" | |
| - "deepspeed/module_inject/containers/unet.py" | |
| - ".github/workflows/nv-sd.yml" | |
| - "requirements/requirements-sd.txt" | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: true | |
| permissions: | |
| contents: read | |
| issues: write | |
| jobs: | |
| sd-tests: | |
| runs-on: [self-hosted, nvidia, a6000] | |
| container: | |
| image: nvcr.io/nvidia/pytorch:23.03-py3 | |
| ports: | |
| - 80 | |
| options: --gpus all --shm-size "8G" | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Check container state | |
| run: | | |
| ldd --version | |
| nvcc --version | |
| nvidia-smi | |
| python -c "import torch; print('torch:', torch.__version__, torch)" | |
| python -c "import torch; print('CUDA available:', torch.cuda.is_available())" | |
| - name: Install transformers | |
| run: | | |
| git clone https://github.com/huggingface/transformers | |
| cd transformers | |
| git rev-parse --short HEAD | |
| python -m pip install . | |
| - name: Install deepspeed | |
| run: | | |
| pip install image-similarity-measures | |
| python -m pip install opencv-python==4.6.* --force-reinstall | |
| python -m pip install docutils==0.18.1 jinja2==3.0 urllib3==1.26.11 ninja | |
| python -m pip install .[dev,1bit,autotuning,sd] | |
| ds_report | |
| - name: Python environment | |
| run: | | |
| python -m pip list | |
| - name: Unit tests | |
| run: | | |
| unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch | |
| cd tests | |
| python -m pytest --color=yes --durations=0 --verbose -rF -m 'stable_diffusion' -k "TestStableDiffusion" unit/ --torch_ver="2.0" --cuda_ver="12" | |
| - name: Open GitHub issue if weekly CI fails | |
| if: ${{ failure() && (github.event_name == 'schedule') }} | |
| uses: JasonEtco/create-an-issue@v2 | |
| env: | |
| GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| with: | |
| filename: .github/ISSUE_TEMPLATE/ci_failure_report.md | |
| update_existing: true |