Jily: Cost-Aware AutoScaling of Heterogeneous GPU for DNN Inference in Public Cloud.

Zhaoxing Wang Xuehai Tang Qiuyang Liu Jizhong Han

Published in: IPCCC (2019)

Keyphrases

probabilistic inference
cloud computing
real time
total cost
inference engine
parallel computing
dynamic bayesian networks
expected cost
parallel computation
neural network
real world
bayesian inference
minimum cost
computing systems
lower cost