$\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design

Item #:

079017-3687

Details

DOI: https://doi.org/10.52202/079017-3687
Author(s): Ruisi Cai, Yeonju Ro, Geon-Woo Kim, Peihao Wang, Babak Bejnordi, Aditya Akella, Zhangyang Wang
Pages: 116126-116148 (23 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/079017-3687
Author(s): Ruisi Cai, Yeonju Ro, Geon-Woo Kim, Peihao Wang, Babak Bejnordi, Aditya Akella, Zhangyang Wang
Pages: 116126-116148 (23 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)