SC '21 | Ribbon: Cost-Effective and QoS-Aware Deep Learning Model Inference Using a Diverse Pool of Cloud Computing Instances

[mental2008]

To appear in SC '21.

Authors:
Baolin Li, Rohan Roy, Tirthak Patel, Vijay Gadepally, Karen Gettings, Devesh Tiwari
Northeastern University, Massachusetts Institute of Technology (MIT)