引导式测验 · 中等 等级

推测性解码测验

涵盖草稿和验证解码、精确目标分布保存、接受率限制以及加速的实际测量。

相关引导路径推测性解码
问题 1 的 8

推测性解码如何加速大型模型的生成？

预览每个问题8 问题

当您参加测验时，就会出现答案和解释。

  1. 推测性解码如何加速大型模型的生成？
    • 小型草稿模型猜测大型模型并行验证的几个标记
    • 将模型永久压缩到一半大小
    • 移除注意力机制
    • 使用更多数据训练模型
  2. 对于低批量大小的大型模型，为什么单令牌自回归解码会很慢？
    • Each token requires internet access
    • Repeated reads of large model weights can make decoding memory-bandwidth bound
    • The model permanently stores a full copy of every possible output
    • The tokenizer performs the model’s matrix multiplications
  3. 在贪婪推测解码中，草稿和目标预测不一致的第一个标记会发生什么？
    • The whole conversation is thrown away and restarted from scratch
    • 草稿模型立即重新训练
    • The matching prefix is kept, the target token is used at the mismatch, and later draft tokens are discarded
    • 输出质量永久下降
  4. 在精确推测采样下，输出分布与仅从目标模型采样相比如何？
    • It is always lower quality but faster
    • It is identical only when the draft model is larger
    • It becomes deterministic regardless of target sampling
    • It is identical in distribution
  5. 最直接决定推测解码加速的因素是什么？
    • 模型草案猜测的接受率
    • GPU的颜色
    • 型号名称的长度
    • 一天中的时间
  6. 美杜莎和 EAGLE 在方法上有什么共同点？
    • 他们需要量子硬件
    • 它们消除了对单独的草稿模型的需要
    • 他们删除目标模型
    • 他们只处理图像
  7. What should a serving team measure before claiming speculative decoding will speed up its workload?
    • Only the target model’s parameter count
    • Only whether the draft produces fluent text
    • Draft cost, target verification cost, accepted tokens and end-to-end latency under representative traffic
    • The number of tokenizer files
  8. In exact speculative sampling, what happens when a proposed token is rejected?
    • The whole conversation is discarded
    • The target model is permanently changed
    • The rejected token is kept without verification
    • A correction step samples from the distribution needed to preserve the target model’s output distribution