{
  "lesson": "22-load-testing-llm-apis",
  "title": "Load Testing LLM APIs — Why k6 and Locust Lie",
  "questions": [
    {
      "stage": "pre",
      "question": "What is the GIL trap in Locust-based LLM load testing?",
      "options": [
        "Locust only works on Windows",
        "Locust does not support HTTP",
        "Client-side tokenization runs under the Python GIL and queues behind request generation, inflating reported inter-token latency",
        "Locust requires CUDA"
      ],
      "correct": 2,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "What is the prompt-uniformity trap?",
      "options": [
        "Uniform prompts always slow the server down",
        "Sampling from a real distribution under-represents long prompts",
        "Uniform prompts require streaming",
        "Looping the same prompt makes prefix caching look like full concurrent decode, inflating reported throughput"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "Which four load patterns does the lesson recommend?",
      "options": [
        "Constant 1 RPS for 10 days",
        "Manual click tests",
        "Steady-state, ramp, spike, soak",
        "Burst only"
      ],
      "correct": 2,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "How does the lesson recommend building a realistic prompt distribution?",
      "options": [
        "Sample from a real distribution using mean and stddev (for example LLMPerf's --mean-input-tokens / --stddev-input-tokens) or replay real traffic",
        "Random characters per request",
        "Hand-write 5 prompts and shuffle",
        "Always use the same prompt to maximize cache hits"
      ],
      "correct": 0,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "Which 2026 tool combination is positioned as best for CI/CD SLA gates and Kubernetes-native distributed runs?",
      "options": [
        "k6 v2026.1.0 with the k6 Operator 1.0 GA (TestRun / PrivateLoadZone CRDs)",
        "guidellm only",
        "Vegeta only",
        "Locust 2.43.3 stock"
      ],
      "correct": 0,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "Which failure mode does the soak load pattern catch?",
      "options": [
        "Memory leaks, connection-pool drift, and observability overflow over hours",
        "Cold-start tail",
        "Tokenizer GIL contention",
        "Cache eviction storms"
      ],
      "correct": 0,
      "explanation": ""
    }
  ]
}