DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dehghanighobadi, Zahra, Fischer, Asja
Format:	Preprint
Published:	2026
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/2604.24647