Distributed trt-llm #250
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 Pytorch 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_pytorch_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, 'pytorch') || | |
| contains( github.event.pull_request.labels.*.name, 'single_gpu') || | |
| contains( github.event.pull_request.labels.*.name, 'cli_cuda_pytorch_single_gpu') | |
| }} | |
| runs-on: [single-gpu, nvidia-gpu, a10, ci] | |
| container: | |
| image: ghcr.io/huggingface/optimum-benchmark:latest-cuda | |
| options: --ipc host --gpus all | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Install dependencies | |
| run: | | |
| pip install -e .[testing,diffusers,timm,peft,bitsandbytes,autoawq,auto-gptq] | |
| - name: Run tests | |
| run: | | |
| pytest tests/test_cli.py -x -s -k "cli and cuda and pytorch and not (dp or ddp or device_map or deepspeed)" | |
| run_cli_cuda_pytorch_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, 'pytorch') || | |
| contains( github.event.pull_request.labels.*.name, 'multi_gpu') || | |
| contains( github.event.pull_request.labels.*.name, 'cli_cuda_pytorch_multi_gpu') | |
| }} | |
| runs-on: [multi-gpu, nvidia-gpu, 4-a10, ci] | |
| container: | |
| image: ghcr.io/huggingface/optimum-benchmark:latest-cuda | |
| options: --ipc host --gpus all | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Install dependencies | |
| run: | | |
| pip install -e .[testing,diffusers,timm,peft,deepspeed] | |
| - name: Run tests (parallel) | |
| run: | | |
| pytest tests/test_cli.py -x -s -k "cli and cuda and pytorch and (dp or ddp or device_map)" | |
| - name: Run tests (sequential) | |
| run: | | |
| FORCE_SEQUENTIAL=1 pytest tests/test_cli.py -x -s -k "cli and cuda and pytorch and (deepspeed_inference)" |