← Search

Fanjin Zhang

2 accepted papers

2025

SAM Decoding: Speculative Decoding via Suffix Automaton

ACL 2025long

Speculative decoding (SD) has been demonstrated as an effective technique for lossless LLM inference acceleration.Retrieval-based SD methods, one kind of model-free method, have yielded promising speedup, but they often rely on single retrieval resources, inefficient retrieval methods, and are const…