Serve hundreds to thousands of ML models — architectures from industry

Serve hundreds to thousands of ML models — architectures from industry

When you only have one or two models to deploy, you can simply put your models in a serving framework and deploy your models on a couple of instances/containers. However, if your ML use cases grow or you build separate models on many segments of your data (like per-customer models), you may eventually need to serve a large number of models. This post will explore the question: How do …

editors pick industry machine learning machine-learning-systems ml ml models ml-platform notes-from-industry serve