CoFRIS: Coordinated Frequency and Resource Scaling for GPU Inference Servers.

Marcus Chow Daniel Wong

Published in: IGSC (2023)

Keyphrases

resource allocation
probabilistic inference
bayesian networks
multi agent
real time
resource constraints
inference mechanism
inference engine
disk space
scalable distributed
graphics hardware
inference process
parallel implementation
low frequency
data center
cooperative
databases
load balance
gpu accelerated