Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2410.19123
Cited By
Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
24 October 2024
Ruisi Cai
Yeonju Ro
Geon-Woo Kim
Peihao Wang
Babak Ehteshami Bejnordi
Aditya Akella
Zhilin Wang
MoE
Re-assign community
ArXiv
PDF
HTML
Papers citing
"Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design"
2 / 2 papers shown
Title
Life-Cycle Routing Vulnerabilities of LLM Router
Qiqi Lin
Xiaoyang Ji
Shengfang Zhai
Qingni Shen
Zhi-Li Zhang
Yuejian Fang
Yansong Gao
AAML
59
1
0
09 Mar 2025
fMoE: Fine-Grained Expert Offloading for Large Mixture-of-Experts Serving
Hanfei Yu
Xingqi Cui
H. M. Zhang
Hairu Wang
Hao Wang
MoE
61
0
0
07 Feb 2025
1