Cost-Efficient Serverless Inference Serving with Joint Batching and Multi-Processing.

Shen Cai Zhi Zhou Kongyange Zhao Xu Chen

Published in: APSys (2023)

Keyphrases

cost efficient
real time
batch processing
databases
scheduling problem
data sets
information processing
probabilistic inference
inference engine
governmental organizations
artificial intelligence
bayesian networks
data processing
bayesian inference
inference process