What is ML Lambda?
ML Lambda is an open source model management cluster for deploying, serving and monitoring machine learning models and ad-hoc algorithms. It enables you to get your models up and running in an instant on just about any infrastructure and using any of the available machine learning toolkits. It lets you monitor your models’ performance, analyse their inputs (for example, determine whether there is recently an increased number of outliers or not), observe models’ inference on given data and many more.
- Getting Started page will help you to quickly set up and deploy your first model with ML Lambda.
- Models page will explain you the main principles of working with your models and show you how to upload TensorFlow, Keras, Spark or any other arbitrary model within Python runtime.
- All models run on top of Runtimes. If you can’t find a desired runtime for your purposes, you can develop your own runtime for any language via RPC service.