Alex Kogan
Improving Inference Performance of Machine Learning with the Divide-and-Conquer Principle
Many popular machine learning models scale poorly when deployed on CPUs. In this talk I will discuss the reasons behind that and propose a simple, yet effective approach based on the well-known Divide-and-Conquer Principle to tackle this problem of great practical importance. Given an inference job, instead of using all available computing resources (i.e., CPU cores) for running it, the idea is to break the job into independent parts that can be executed in parallel, each with the number of cores according to its expected computational cost. I will talk about the implementation of this idea in the popular OnnxRuntime framework and discuss evaluation results of its effectiveness with several use cases, including the well-known models for optical character recognition (PaddleOCR) and natural language processing (BERT).
back to overview
Watch Recording
