id: TC-RUNTIME-002
name: GPU Detection
suite: runtime
priority: 2
timeout: 120000

dependencies:
  - TC-RUNTIME-001

steps:
  - name: Check nvidia-smi inside container
    command: docker exec ollama37 nvidia-smi

  - name: Check CUDA libraries
    command: docker exec ollama37 ldconfig -p | grep -i cuda | head -5

  - name: Check UVM device files (create if missing)
    command: |
      if [ ! -e /dev/nvidia-uvm ]; then
        echo "UVM device missing, creating with nvidia-modprobe..."
        sudo nvidia-modprobe -u -c=0
        echo "Restarting container to pick up UVM devices..."
        cd docker && docker compose restart
        sleep 15
      else
        echo "UVM device exists: $(ls -l /dev/nvidia-uvm)"
      fi

  - name: Check Ollama GPU detection in logs
    command: |
      cd docker && docker compose logs 2>&1 | grep -E "(inference compute|GPU detected)" | tail -5

criteria: |
  Tesla K80 GPU should be detected by both nvidia-smi AND Ollama CUDA runtime.

  Expected:
  - nvidia-smi shows Tesla K80 GPU(s) with Driver 470.x
  - CUDA libraries are available (libcuda, libcublas, etc.)
  - /dev/nvidia-uvm device file exists (required for CUDA runtime)
  - Ollama logs show GPU detection, NOT "id=cpu library=cpu"

  NOTE: If nvidia-smi works but Ollama shows only CPU, the UVM device
  files are missing. The test will auto-fix with nvidia-modprobe -u -c=0.

  The K80 has 12GB VRAM per GPU. Accept variations in reported memory.