"Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on ..."

Zheng Wang et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2407.08454

access: open

type: Informal or Other Publication

metadata version: 2024-08-16

a service of  Schloss Dagstuhl - Leibniz Center for Informatics