roboflow--rf-detr/.github/workflows/ci-tests-gpu.yml

name: GPU tests Workflow

on:
  push:
    branches: ["main", "release/*", "develop", "feat/*"]
  pull_request:
    types: [opened, synchronize, reopened, ready_for_review]

permissions:
  contents: read
defaults:
  run:
    shell: bash

env:
  PYTHON_VERSION: "3.12"
  # UV_TORCH_BACKEND only works with 'uv pip' commands, not 'uv sync'.
  # Set to "auto" for GPU workflow (auto-detects CUDA version).
  UV_TORCH_BACKEND: "auto"

concurrency:
  group: pytest-gpu-test-${{ github.ref }}
  cancel-in-progress: ${{ github.event_name == 'pull_request' }}

jobs:
  run-gpu-tests:
    name: Testing
    if: github.event_name == 'push' || !github.event.pull_request.draft
    timeout-minutes: 35
    runs-on: Roboflow-GPU-VM-Runner
    steps:
      - name: 🖥️ Print GPU information
        run: nvidia-smi
      - name: 🧰 Install build tools
        run: |
          sudo apt-get update
          sudo apt-get install -y cmake
      - name: 📥 Checkout the repository
        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1

      - name: 🐍 Install uv and set Python version
        uses: astral-sh/setup-uv@61cb8a9741eeb8a550a1b8544337180c0fc8476b # v7.2.0
        with:
          python-version: ${{ env.PYTHON_VERSION }}
          activate-environment: true

      - name: 🚀 Install Packages
        timeout-minutes: 5
        # Use uv pip install (not uv sync) to avoid universal lock resolution failing on
        # extras that require Python>=3.12 (e.g. tflite/onnx2tf) when project supports >=3.10.
        # UV_TORCH_BACKEND=auto (set above) works only with uv pip, not uv sync.
        run: uv pip install -e ".[onnx,plus,train,visual]" --group tests --group ci-gpu-pin

      - name: 🧪 Run the Test
        run: |
          uv run --no-sync pytest tests/ \
          -m gpu \
          -n 3 \
          --reruns 1 --only-rerun "OutOfMemoryError" \
          --cov=rfdetr --cov-report=xml \
          --timeout=600 \
          --durations=20

      - name: Upload coverage to Codecov
        uses: codecov/codecov-action@75cd11691c0faa626561e295848008c8a7dddffe # v5
        with:
          token: ${{ secrets.CODECOV_TOKEN }}
          files: "coverage.xml"
          flags: gpu,${{ runner.os }},py${{ env.PYTHON_VERSION }}
          env_vars: OS,PYTHON
          name: codecov-umbrella
          fail_ci_if_error: false

      - name: Minimize uv cache
        run: uv cache prune --ci