Story
arxiv_cs_cl · Oct 7, 2026 · paper
Source brief
Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds
arxiv.orgOct 7, 2026
original source linked
In brief
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) draft...
Feed lens
eval