A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities

TL;DR

This survey reviews the challenges and opportunities in optimizing large-scale deep learning serving systems, highlighting recent advances and proposing a taxonomy to guide future research in this rapidly evolving field.

Contribution

It introduces a novel taxonomy for large-scale DL serving system challenges and summarizes recent optimization techniques and computing paradigms.

Findings

Identification of key challenges in LDS systems

Summary of recent optimization techniques

Proposed taxonomy for system challenges

Abstract

Deep Learning (DL) models have achieved superior performance in many application domains, including vision, language, medical, commercial ads, entertainment, etc. With the fast development, both DL applications and the underlying serving hardware have demonstrated strong scaling trends, i.e., Model Scaling and Compute Scaling, for example, the recent pre-trained model with hundreds of billions of parameters with ~TB level memory consumption, as well as the newest GPU accelerators providing hundreds of TFLOPS. With both scaling trends, new problems and challenges emerge in DL inference serving systems, which gradually trends towards Large-scale Deep learning Serving systems (LDS). This survey aims to summarize and categorize the emerging challenges and optimization opportunities for large-scale deep learning serving systems. By providing a novel taxonomy, summarizing the computing paradigms, and elaborating the recent technique advances, we hope that this survey could shed light on new optimization perspectives and motivate novel works in large-scale deep learning system optimization.