Login / Signup
FaaSwap: SLO-Aware, GPU-Efficient Serverless Inference via Model Swapping.
Minchen Yu
Ao Wang
Dong Chen
Haoxuan Yu
Xiaonan Luo
Zhuohao Li
Wei Wang
Ruichuan Chen
Dapeng Nie
Haoran Yang
Published in:
CoRR (2023)
Keyphrases
</>
computational model
real time
experimental data
inference mechanism
bayesian model
prediction model
mathematical model
management system
high level
neural network
theoretical analysis
parameter estimation
em algorithm
multi agent
prior information
formal model
probabilistic inference
data sets