GPU inference In a previous article, I illustrated how to serve a PyTorch model in a serverless manner on AWS lambda. However, currently AWS lambda and other serverless compute functions usually run on the CPU. But what if you need to serve your machine learning model on the GPU during your inference and the CPU just doesn’t cut it? In this article, I will show you how to use Docker to serve your PyTorch model for GPU inference and also provide it as a REST API.

PyTorch is great to quickly prototype your ideas and get up and running with deep learning. Since it is very pythonic, you can simply debug it in PyCharm as you are used to in regular Python. However, when it comes to serving your model in production the question arises: how to do it? There are many possibilities to do so, but in this post, you will learn how to serve it as a lambda function in a serverless manner on AWS.