Improving Throughput-oriented Generative Inference with CPUs.

Daon Park Sungbin Jo Bernhard Egger

Published in: APSys (2023)

Keyphrases

response time
probabilistic inference
inference process
generative model
parallel processing
bayesian inference
inference engine
inference mechanism
probability distribution
sensor networks
general purpose
data driven
belief networks
probabilistic reasoning
dynamic bayesian networks
efficient learning