Z

Zeliang Zhang, Nikhil Ghosh, Jiani Liu, Bin Yu, Xiaodong Liu

Zeliang Zhang, Nikhil Ghosh, Jiani Liu, Bin Yu, Xiaodong Liu의 전문분석자료

Academic · 약 1분

Does a Global Perspective Help Prune Sparse MoEs Elegantly?

arXiv:2604.06542v1 Announce Type: new Abstract: Empirical scaling laws for language models have encouraged the development of ever-larger LLMs, despite their growing computational and memory costs. …

Zeliang Zhang, Nikhil Ghosh, Jiani Liu, Bin Yu, Xiaodong Liu
조회수 80회