SAM Decoding: Speculative Decoding via Suffix Automaton
Abstract: 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 achieved promising speedup,
but these methods often rely on incomplete retrieval resources, inefficient retrieval methods, and are constrained to certain domains.
This paper presents a novel retrieval-based speculative decoding method that adapts suffix automaton (SAM) for efficient and accurate draft generation by utilizing common text corpus and dynamic text sequence.
Unlike existing n-gram matching methods, SAM-Decoding finds the exact longest suffix match, achieving an average time complexity of O(1) per generation step of SAM update and suffix retrieval.
It can also integrate with existing methods, adaptively selecting a draft generation strategy based on match length to generalize to broader domains.
Extensive experiments on Spec-Bench show that our method is $18$\%+ faster than other retrieval-based SD methods. Additionally, when combined with advanced EAGLE-2, it provides an additional speedup of $3.28$\% -- $11.13$\% across various-sized LLM backbones.
Paper Type: Long
Research Area: Generation
Research Area Keywords: inference method, efficient models
Contribution Types: NLP engineering experiment, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models
Languages Studied: English
Submission Number: 287
Loading