Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding 文章

ArXiv CS.CL2026-06-02NEWSen作者: Xin Su, Dawid Majchrowski, Fangyuan Yu, Vanshil Atul Shah, Sebastian Rogawski, Pawel Morkisz, Anahita Bhiwandiwalla, Phillip Howard
查看原文 →
关系图谱

Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding · 相关技术

相关技术

Hybrid Verified DecodingSpeculative decodingautoregressive decodingLarge language model (LLM)