GELATO: Generative Entropy- and Lyapunov-based Adaptive Token Offloading for Device-Edge Speculative LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Zengzipeng, Sun, Yuxuan, Chen, Wei, Ding, Jianwen, Ai, Bo
Format:	Preprint
Published:	2026
Subjects:	Networking and Internet Architecture Distributed, Parallel, and Cluster Computing Information Theory Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.10124