Subkv: Quantizing Long Context KV Cache for Sub‐Billion Parameter Language Models on Edge Devices
Year: 2025
Type: article
Source: Software Practice and Experience
DOI: 10.1002/spe.3422
Authors: Ziqian Zeng, Tao Zhang, Zhengdong Lu, Wenjun Li, Huiping Zhuang, Hongen Shao, Sin G. Teo, Xiaofeng Zou
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: closed
OpenAlex ID: W4409108393
