Speculative decoding does not let the model guess blindly. A cheap draft model proposes tokens, while the target model verifies them in parallel. The real question is whether acceptance rate and batch size make it worthwhile.
推测解码不是让大模型乱猜,而是用草稿模型先给候选,再由目标模型一次性验证。理解 Medusa、EAGLE 和大 Batch 的关系,才能判断它在生产高并发里是否真的划算。