Know Your Enemy To Save Cloud Energy:
Energy-Performance Characterization of Machine Learning Serving
This is the artifact repository for the HPCA'23 paper "Know Your Enemy To Save Cloud Energy: Energy-Performance Characterization of Machine Learning Serving". The prototype and the simulation code are available.
The prototype inference server is based on the Triton Inference Server v2.7.0 (TIS). The source code is available here.
The simulation was performed based on the values obtained from the prototype to observe the effectiveness of the proposed schemes in the cloud-scale environment. The source code is available here.
@INPROCEEDINGS{yu2023know,
author={Yu, Junyeol and Kim, Jongseok and Seo, Euiseong},
title={Know Your Enemy To Save Cloud Energy: Energy-Performance Characterization of Machine Learning Serving},
booktitle={2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)},
year={2023},
pages={842-854},
doi={10.1109/HPCA56546.2023.10070943}}
If you have any questions, please contact [email protected]