QoS-Aware Scheduling of Heterogeneous Servers for Inference in Deep Neural Networks.

@inproceedings{fang-2017-qosaware, author = {Zhou Fang and Tong Yu and Ole J. Mengshoel and Rajesh K. Gupta}, editor = {Ee-Peng Lim and Marianne Winslett and Mark Sanderson and Ada Wai-Chee Fu and Jimeng Sun and J. Shane Culpepper and Eric Lo and Joyce C. Ho and Debora Donato and Rakesh Agrawal and Yu Zheng and Carlos Castillo and Aixin Sun and Vincent S. Tseng and Chenliang Li}, title = {{QoS-Aware Scheduling of Heterogeneous Servers for Inference in Deep Neural Networks}}, booktitle = {{Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, CIKM 2017, Singapore, November 06 - 10, 2017}}, pages = {2067--2070}, publisher = {ACM}, year = {2017}, url = {https://doi.org/10.1145/3132847.3133045}, doi = {https://doi.org/10.1145/3132847.3133045} }