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

Authors:

Top Cited Papers
Open Access
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. While simply ”patching” general serverless systems does not resolve the problem completely, we propose that such a system should natively combine the features of inference with a serverless paradigm. We present INFless, the first ML domain-specific serverless platform. It provides a unified, heterogeneous resource abstraction between CPU and accelerators, and achieves high throughput using built-in batching and non-uniform scaling mechanisms. It also supports low latency through coordinated management of batch queuing time, execution time and coldstart rate. We evaluate INFless using both a local cluster testbed and a large-scale simulation. Experimental results show that INFless outperforms state-of-the-art systems by 2×-5× on system throughput, meeting the latency goals of ML services.