Yun-Xiao Zhao

Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds

Speculative decoding accelerates large language model inference by using a low-cost draft model to propose tokens that the full-size target model verifies in parallel. Parallel and semi-autoregressive (semi- AR) drafters improve drafting efficiency by proposing an entire block in a single forward pass, but training the...