引導式測驗 · 中等 等級
推測性解碼測驗
涵蓋草稿和驗證解碼、精確目標分佈保存、接受率限制以及加速的實際測量。
問題 1 的 8
推測性解碼如何加速大型模型的產生?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 推測性解碼如何加速大型模型的產生?
- 小型草稿模型猜測大型模型並行驗證的幾個標記
- 將模型永久壓縮到一半大小
- 移除注意力機制
- 使用更多資料訓練模型
- For a large model at low batch size, why can one-token autoregressive decoding be slow?
- 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
- In greedy speculative decoding, what happens at the first token where draft and target predictions disagree?
- The whole conversation is thrown away and restarted from scratch
- 草稿模型立即重新訓練
- The matching prefix is kept, the target token is used at the mismatch, and later draft tokens are discarded
- 輸出品質永久下降
- Under exact speculative sampling, how does the output distribution compare with sampling from the target model alone?
- 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
- 最直接決定推測解碼加速的因素是什麼?
- 模型草案猜測的接受率
- GPU的顏色
- 型號名稱的長度
- 一天中的時間
- 美杜莎和 EAGLE 在方法上有什麼共同點?
- 他們需要量子硬體
- 它們消除了對單獨的草稿模型的需要
- 他們刪除目標模型
- 他們只處理圖像
- 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
- 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