InferAll: Coordinated optimization for machine learning inference serving in public cloud.
This repo provides an event-driven based simulator with initial execution baseline prepared on AWS EC2 and AWS serverless.
If this project was helpful, please consider citing:
@phdthesis{kumar2021inferall,
title={Inferall: coordinated optimization for machine learning inference serving in public cloud},
author={Kumar, Pramod},
year={2021},
school={Pennsylvania State University}
}
@INPROCEEDINGS{8814535,
author={Gunasekaran, Jashwant Raj and Thinakaran, Prashanth and Kandemir, Mahmut Taylan and Urgaonkar, Bhuvan and Kesidis, George and Das, Chita},
booktitle={2019 IEEE 12th International Conference on Cloud Computing (CLOUD)},
title={Spock: Exploiting Serverless Functions for SLO and Cost Aware Resource Procurement in Public Cloud},
year={2019},
volume={},
number={},
pages={199-208},
doi={10.1109/CLOUD.2019.00043}}
The paper can be downloaded from https://etda.libraries.psu.edu/catalog/18975pjk5502