"Subkv: Quantizing Long Context KV Cache for Sub-Billion Parameter Language ..."

Ziqian Zeng et al. (2025)

> Home

Details and statistics

DOI: 10.1002/SPE.3422

access: closed

type: Journal Article

metadata version: 2025-08-09

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - journals/spe/ZengZLLZSTZ25
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/spe/ZengZLLZSTZ25
Ziqian Zeng, Tao Zhang, Zhengdong Lu, Wenjun Li, Huiping Zhuang, Hongen Shao, Sin G. Teo, Xiaofeng Zou:
Subkv: Quantizing Long Context KV Cache for Sub-Billion Parameter Language Models on Edge Devices. Softw. Pract. Exp. 55(8): 1287-1304 (2025)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.