Saved in:
Bibliographic Details
Main Authors: Bozorgkhoo, Amirhossein, Molybog, Igor
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.11053
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Speculative decoding is a technique that uses multiple language models to accelerate infer- ence. Previous works have used an experi- mental approach to optimize the throughput of the inference pipeline, which involves LLM training and can be costly. This study of spec- ulative decoding proposes a theory that ana- lytically connects the key hyperparameters of pre-trained LLMs to the throughput efficiency of a downstream SD-based inference system. The theory allows the prediction of throughput- optimal hyperparameters for the components of an inference system before their pre-training.