Litcius/Paper detail

INFless: a native serverless system for low-latency, high-throughput inference

Yanan Yang, Laiping Zhao, Yiming Li, Huanyu Zhang, Jie Li, Mingyang Zhao, Xingzhen Chen, Keqiu Li

2022128 citationsDOI

Abstract

Modern websites increasingly rely on machine learning (ML) to improve their business efficiency. Developing and maintaining ML services incurs high costs for developers. Although serverless systems are a promising solution to reduce costs, we find that the current general purpose serverless systems cannot meet the low latency, high throughput demands of ML services.

Topics & Concepts

Computer scienceLatency (audio)ThroughputLow latency (capital markets)InferenceComputer networkTelecommunicationsArtificial intelligenceWirelessIoT and Edge/Fog ComputingAdvanced Data Storage TechnologiesCaching and Content Delivery
INFless: a native serverless system for low-latency, high-throughput inference | Litcius