Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xiao, Qingfa, Wang, Jiachuan, Li, Haoyang, Deng, Cheng, Tang, Jiaqi, Li, Shuangyin, Zhang, Yongqi, Wang, Jun, Chen, Lei
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.13542