Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Xingyang, Liu, Jie, Chen, Shaowei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!