MoE-Infinity: Activation-Aware Expert Offloading for Efficient MoE Serving.

Leyang Xue Yao Fu Zhan Lu Luo Mai Mahesh K. Marina

Published in: CoRR (2024)

Keyphrases

website
information processing
computationally intensive
real time
data sets
artificial intelligence
information systems
bayesian networks
information technology
xml documents
data model
hidden markov models
lightweight
computationally efficient
human experts