作者位次 #2/4ACL 2026Poster· Natural Language Processing
T oken T iming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs
Sibo Xiao · Fu Jinyuan · Zhongle Xie · Lidan Shou
摘要
Accelerating the inference of large language models (LLMs) has been a critical challenge in generative AI. Speculative decoding (SD) substantially improves LLM inference efficiency. However, its utility is limited by a fundamental constraint: the draft and target models must share the same vocabu...