Temperature-centric investigation of speculative decoding with knowledge distillation

Speculative decoding stands as a pivotal technique to expedite inference in autoregressive (large) language models. This method employs a smaller \textit{draft} model to speculate a block of tokens, which the \textit{target} model then evaluates for acceptance. Despite a wealth of studies aimed at increasing the efficiency of speculative decoding, the influence of generation configurations on the decoding process remains poorly understood, especially concerning decoding temperatures. This paper delves into the effects of decoding temperatures on speculative decoding’s efficacy. Beginning with knowledge distillation (KD), we first highlight the challenge of decoding at higher temperatures, and demonstrate KD in a consistent temperature setting could be a remedy. We also investigate the effects of out-of-domain testing sets with out-of-range temperatures. Building upon these findings, we take an initial step to further the speedup for speculative decoding, particularly in a high-temperature generation setting. Our work offers new insights into how generation configurations drastically affect the performance of speculative decoding, and underscores the need for developing methods that focus on diverse decoding configurations. Code is publicly available at \texttt{\url{https://github.com/ozyyshr/TempSpec}}.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois Urbana-Champaign

Year dc:date

2025

Author dc:creator

• Ouyang, Siru

Contributors dc:contributor

• Han, Jiawei

• Speculative Decoding
• Knowledge Distillation
• Large Language Models

Statement dc:rights

• Copyright 2025 Siru Ouyang

Language dc:language

en

Handle dc:identifier

https://hdl.handle.net/2142/132610

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/132610