Quantize-Sample-and-Verify: LLM Acceleration via Adaptive Edge-Cloud Speculative Decoding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Guangyi, Cai, Yunlong, Yu, Guanding, Popovski, Petar, Simeone, Osvaldo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items