HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference
Paper
•
2411.01433
•
Published
•
1
Liu
beannn
·
AI & ML interests
None yet
Recent Activity
authored
a paper
about 2 months ago
A Survey on Inference Optimization Techniques for Mixture of Experts
Models
authored
a paper
about 2 months ago
HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE
Inference
upvoted
a
paper
about 2 months ago
HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE
Inference
Organizations
None yet
upvoted
a
paper
about 2 months ago