WattWiser: Power & Resource-Efficient Scheduling for Multi-Model Multi-GPU Inference Servers.

Ali Jahanshahi Mohammadreza Rezvani Daniel Wong

Published in: IGSC (2023)

Keyphrases

prior knowledge
real time
genetic algorithm
computational model
high level
objective function
probabilistic model
probability distribution
scheduling problem
management system
mathematical model
statistical model
resource allocation
resource constraints
dynamic bayesian networks