SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tian, Jiayi, Azizi, Seyedarmin, Zhao, Yequan, Potraghloo, Erfan Baghaei, McPherson, Sean, Sridhar, Sharath Nittur, Wang, Zhengyang, Zhang, Zheng, Pedram, Massoud, Kundu, Souvik
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2512.07993