Improving Memory Utilization by Sharing DNN Models for Serverless Inference

Conference Object

Abstract: Serving deep neural network (DNN) models requires a lot of memory and has a relatively long response

Palabras claves:

CLOUD COMPUTING, DNN Inference, serverless

Autores:

Eunyoung Lee, Kim M.H., Lee J., Yu H.C.

Fuentes:

scopus