Why Smaller Is Slower? Dimensional Misalignment in Compressed LLMs

辛继灏, Tian Lyu, Qilong Pan, Kesen Wang, Marco Canini
三月, 2026
引用 代码
类型
会议文章
出版物
EuroMLSys 2026
辛继灏
辛继灏
Ph.D. Student in Machine Learning Systems