Refactor llm perf backend handling #255
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: CLI CUDA Torch-ORT Tests | |
| on: | |
| workflow_dispatch: | |
| push: | |
| branches: | |
| - main | |
| pull_request: | |
| branches: | |
| - main | |
| types: | |
| - opened | |
| - reopened | |
| - synchronize | |
| - labeled | |
| - unlabeled | |
| concurrency: | |
| cancel-in-progress: true | |
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} | |
| jobs: | |
| run_cli_cuda_torch_ort_single_gpu_tests: | |
| if: ${{ | |
| (github.event_name == 'push') || | |
| (github.event_name == 'workflow_dispatch') || | |
| contains( github.event.pull_request.labels.*.name, 'cli') || | |
| contains( github.event.pull_request.labels.*.name, 'cuda') || | |
| contains( github.event.pull_request.labels.*.name, 'torch_ort') || | |
| contains( github.event.pull_request.labels.*.name, 'single_gpu') || | |
| contains( github.event.pull_request.labels.*.name, 'cli_cuda_torch_or_single_gpu') | |
| }} | |
| runs-on: [single-gpu, nvidia-gpu, a10, ci] | |
| container: | |
| image: ghcr.io/huggingface/optimum-benchmark:latest-cuda-ort | |
| options: --ipc host --gpus all | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Install dependencies | |
| run: | | |
| pip install -e .[testing,torch-ort,peft] | |
| pip install optimum@git+https://github.com/huggingface/optimum.git | |
| - name: Run tests | |
| run: | | |
| pytest -x -s -k "cli and cuda and torch_ort and not (dp or ddp or device_map) and not (peft)" | |
| run_cli_cuda_torch_ort_multi_gpu_tests: | |
| if: ${{ | |
| (github.event_name == 'push') || | |
| (github.event_name == 'workflow_dispatch') || | |
| contains( github.event.pull_request.labels.*.name, 'cli') || | |
| contains( github.event.pull_request.labels.*.name, 'cuda') || | |
| contains( github.event.pull_request.labels.*.name, 'torch_ort') || | |
| contains( github.event.pull_request.labels.*.name, 'multi_gpu') || | |
| contains( github.event.pull_request.labels.*.name, 'cli_cuda_torch_ort_multi_gpu') | |
| }} | |
| runs-on: [multi-gpu, nvidia-gpu, 4-a10, ci] | |
| container: | |
| image: ghcr.io/huggingface/optimum-benchmark:latest-cuda-ort | |
| options: --ipc host --gpus all | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Install dependencies | |
| run: | | |
| pip install -e .[testing,torch-ort,peft] | |
| pip install optimum@git+https://github.com/huggingface/optimum.git | |
| - name: Run tests | |
| run: | | |
| pytest -x -s -k "cli and cuda and torch_ort and (dp or ddp or device_map) and not (peft)" |