WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tao, Wei, Qu, Xiaoyang, Wang, Peiqiang, Li, Guokuan, Wan, Jiguang, Lu, Kai, Wang, Jianzong
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.02262