{
  "lesson": "07-tensorrt-llm-blackwell",
  "title": "Hardware-Specialized Inference Compilation — FP8 and NVFP4 on Blackwell",
  "questions": [
    {
      "stage": "pre",
      "question": "Roughly what is the per-million-tokens cost gap the lesson reports between Blackwell + TRT-LLM + Dynamo and H100 + vLLM on a comparable 120B-class workload?",
      "options": [
        "About 2x",
        "About 7x",
        "About 1.1x",
        "About 100x"
      ],
      "correct": 1,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "Why does the lesson recommend keeping KV cache in FP8 rather than NVFP4 on Blackwell?",
      "options": [
        "NVFP4 KV cache is not yet supported in any engine",
        "KV cache spans a wide dynamic range; FP4 quantization causes catastrophic accuracy loss in attention scores",
        "FP8 uses less memory than FP4",
        "FP8 is the only precision NVLink 5 supports"
      ],
      "correct": 1,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "Which Blackwell feature does TRT-LLM exploit so models can be loaded without a post-training conversion step?",
      "options": [
        "BF16 KV cache",
        "FP64 attention",
        "INT2 weights via bitsandbytes",
        "Day-0 FP4 weights shipped by model providers"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "What is the dominant tradeoff of choosing the TRT-LLM stack per the lesson?",
      "options": [
        "It requires fully autonomous remediation",
        "It cannot serve MoE models",
        "It only works at small scale",
        "It locks you into NVIDIA hardware — no AMD, no Intel, no ARM"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "Which precision combination does the lesson describe as the typical Blackwell config?",
      "options": [
        "Everything in BF16",
        "Weights NVFP4, activations NVFP4, KV cache FP8, attention accumulator FP32",
        "Weights INT8, activations FP32, KV cache INT4",
        "Weights FP4, KV cache FP4, attention in INT8"
      ],
      "correct": 1,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "For reasoning-heavy workloads where NVFP4 weight conversion drops MATH accuracy a few points, what does the lesson advise?",
      "options": [
        "Switch to AMD MI300X",
        "Disable speculative decoding",
        "Validate task quality on your eval set per model; teams often use FP8 weights + FP4 activations or stay on H200 with FP8 throughout",
        "Ship NVFP4 anyway because the cost win dominates"
      ],
      "correct": 2,
      "explanation": ""
    }
  ]
}