Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
Paper
•
2410.19123
•
Published
•
15
Ruisi Cai
CCCCRS
AI & ML interests
None yet
Recent Activity
authored
a paper
about 2 months ago
Robust Weight Signatures: Gaining Robustness as Easy as Patching
Weights?
authored
a paper
about 2 months ago
H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large
Language Models
authored
a paper
about 2 months ago
Robust Mixture-of-Expert Training for Convolutional Neural Networks
Organizations
