Reducing Machine Learning Inference Cost for PyTorch Models

Level: 200

In deep learning applications, inference accounts for up to 90% of compute cost. To reduce this high inference cost, you can use Amazon Elastic Inference, which allows you to attach just the right amount of GPU-powered inference acceleration to any EC2 or SageMaker instance type or ECS task. In this tech talk, you will learn about how to use Elastic Inference for deploying models built on PyTorch, a popular machine learning framework.