test_cli_cuda_tensorrt_llm.yaml

name: CLI CUDA TensorRT-LLM Tests

on:
  workflow_dispatch:
  push:
    branches:
      - main
    paths:
      - .github/workflows/test_cli_cuda_tensorrt_llm.yaml
      - "optimum_benchmark/**"
      - "docker/**"
      - "tests/**"
      - "setup.py"
  pull_request:
    branches:
      - main
    paths:
      - .github/workflows/test_cli_cuda_tensorrt_llm.yaml
      - "optimum_benchmark/**"
      - "docker/**"
      - "tests/**"
      - "setup.py"

concurrency:
  cancel-in-progress: true
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}

env:
  IMAGE: huggingface/optimum-nvidia:latest

jobs:
  cli_cuda_tensorrt_llm_tests:
    runs-on: [single-gpu, nvidia-gpu, a10, ci]

    steps:
      - name: Checkout
        uses: actions/checkout@v3

      - name: Run tests
        uses: addnab/docker-run-action@v3
        with:
          image: ${{ env.IMAGE }}
          options: |
            --rm 
            --gpus all 
            --shm-size 64G
            --env MKL_THREADING_LAYER=GNU
            --volume ${{ github.workspace }}:/workspace
            --workdir /workspace
          run: |
            pip install -e .[testing]
            pytest -x -s -k "cli and cuda and tensorrt_llm"