Login / Signup
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead.
Rickard Brüel Gabrielsson
Jiacheng Zhu
Onkar Bhardwaj
Leshem Choshen
Kristjan H. Greenewald
Mikhail Yurochkin
Justin Solomon
Published in:
CoRR (2024)
Keyphrases
</>
agent technology
input output
data compression
huge number
multi agent systems
neural network
software agents
electronic commerce
communication overhead
mobile agents
databases
artificial intelligence
distributed systems
description logics
cooperative
decision trees
machine learning
maintenance cost
tcp ip