Layer-wise heterogeneity-guided heterogeneous pruning: An LLM compression method

Abstract Large language models (LLMs) have become foundational in modern natural language processing, enabling diverse applications such as conversational AI, code generation, and scientific discovery. Their massive parameter counts impose significant computational and memory demands, hindering depl...

詳細記述

書誌詳細

主要な著者:	Zhihao Yu, Zuxin Ma, Guowei Shen, Yi Chen, Chun Guo, Xiaoqi Duan, Qing Qian, Yunhe Cui
フォーマット:	Artigo
言語:	Inglês
出版事項:	Springer 2026-04-01
シリーズ:	Journal of King Saud University: Computer and Information Sciences
主題:	Large language models Model compression Network pruning Heterogeneous pruning
オンライン･アクセス:	https://doi.org/10.1007/s44443-026-00724-4
タグ:	タグ追加 タグなし, このレコードへの初めてのタグを付けませんか!