作者位次 #3/9ACL 2026Findings· Findings of ACL
MARS : Unleashing the Power of Speculative Decoding via Margin-Aware Verification
Jingwei Song · Xinyu Wang · Hanbin Wang · Xiaoxuan Lei · TIANYU SHI · Shixin Han · Eric Yang · Xiao-Wen Chang · Lynn Ai
摘要
Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by tightly coupling the drafter with the target model, the verification mechanism itself remains largely unchanged, relyi...