Seldon Core is an open source platform for deploying machine learning models on a Kubernetes cluster.
- Deploy machine learning models in the cloud or on-premise.
- Get metrics and ensure proper governance and compliance for your running machine learning models.
- Create powerful inference graphs made up of multiple components.
- Provide a consistent serving layer for models built using heterogeneous ML toolkits.
- Lets you focus on your model by making it easy to serve on kubernetes
- The same workflow and base API for a range of toolkits such as scikit-learn, tensorflow and R
- Out of the box best-practices for logging, tracing and base metrics, applicable to all models across toolkits
- Support for deployment strategies such as running A/B test and canaries
- Inferences graphs for microservice-based serving strategies such as multi-armed bandits or pre-processing
Documentation can be found here.