{
  "lesson": "11-multi-region-kv-locality",
  "title": "Multi-Region LLM Serving and KV Cache Locality",
  "questions": [
    {
      "stage": "pre",
      "question": "Why is round-robin load balancing actively harmful for cached LLM inference?",
      "options": [
        "Round-robin breaks TLS",
        "Round-robin is only valid for stateful databases",
        "Round-robin requires sticky sessions",
        "A request that does not land on the node holding its prefix pays full prefill cost instead of a cache hit"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "What two inputs does a cache-aware router consume?",
      "options": [
        "Only the user_id and tenant_id",
        "Round-robin counters and TLS keys",
        "KV-cache events from replicas and a prefix hash on the incoming request",
        "Random shuffles and request size"
      ],
      "correct": 2,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "Roughly what is the TTFT gap between a cache hit and a cold prefill on a 2K-token prompt for Llama 3.3 70B FP8?",
      "options": [
        "About 1000x",
        "About 10x (~80 ms vs ~800 ms)",
        "About 1.1x",
        "Identical"
      ],
      "correct": 1,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "Why does cross-region routing not always beat regional routing for cache hits?",
      "options": [
        "Cache-aware routing is impossible across regions",
        "Inter-region routing is forbidden by all hyperscalers",
        "GORGO research found cache hits do not help latency",
        "Network RTT eats much of the saved prefill, e.g. a 220 ms US-APAC RTT cuts a 720 ms saving to ~500 ms"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "What does the lesson cite as the 32% LLM DR failure driver?",
      "options": [
        "Backups that include weights but miss tokenizer files or quantization configs",
        "Region quota exhaustion",
        "Misconfigured load balancers",
        "Unencrypted backups"
      ],
      "correct": 0,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "What does the lesson say about commercial cross-region inference offerings such as Bedrock CRI?",
      "options": [
        "They optimize availability, not TTFT, and treat inference as opaque — you still need an app-layer cache-aware router",
        "They are forbidden under GDPR",
        "They are KV-cache-aware and replace app-layer routing",
        "They only work in us-east-1"
      ],
      "correct": 0,
      "explanation": ""
    }
  ]
}