Sign in
Delay-Aware DNN Inference Throughput Maximization in Edge Computing via Jointly Exploring Partitioning and Parallelism.
Jing Li
Weifa Liang
Yuchen Li
Zichuan Xu
Xiaohua Jia
Published in:
LCN (2021)
Keyphrases
</>
loss probability
response time
edge detection
probabilistic inference
bayesian networks
parallel processing
inference process
objective function
probabilistic model
bayesian inference
weighted graph
traffic patterns
vertex set
transmission delay
queue size