Leveraging KV Similarity for Online Structured Pruning in LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Jungmin, Byeon, Gwangeun, Kim, Yulhwa, Hong, Seokin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!