AHASD: Asynchronous Heterogeneous Architecture for LLM Adaptive Drafting Speculative Decoding on Mobile Devices

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zirui, Ma, Zhihua, Fan, Wenxing, Li, Haibin, Wu, Fulin, Zhang, Xiaochun, Ye, Wenming, Li
Format:	Preprint
Published:	2026
Subjects:	Hardware Architecture Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.25326