Picture for Alireza Sanaee

Alireza Sanaee

Queen Mary University of London

IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency

Add code
Aug 24, 2023
Viaarxiv icon

Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems

Add code
Apr 24, 2023
Viaarxiv icon