CARD: A Cache-Assisted Parallel Speculative Decoding Framework via Query-and-Correct Paradigm for Accelerating LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Enyu, Sheng, Kai, Chen, Hao, He, Xin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.04462