id: TC-INFERENCE-002
name: Basic Inference
suite: inference
priority: 2
timeout: 180000

dependencies:
  - TC-INFERENCE-001

steps:
  - name: Run simple math question
    command: docker exec ollama37 ollama run gemma3:4b "What is 2+2? Answer with just the number." 2>&1
    timeout: 120000

  - name: Check GPU memory usage
    command: docker exec ollama37 nvidia-smi --query-compute-apps=pid,used_memory --format=csv 2>/dev/null || echo "No GPU processes"

criteria: |
  Basic inference should work on Tesla K80.

  Expected:
  - Model responds to the math question
  - Response should indicate "4" (accept variations: "4", "four", "The answer is 4", etc.)
  - GPU memory should be allocated during inference
  - No CUDA errors in output

  This is AI-generated output - accept reasonable variations.
  Focus on the model producing a coherent response.