Use it when
- You want a serving framework that supports a wide range of ML frameworks.
- You want a serving framework that works on multiple implementation languages (R, Julia, C++, Java, and Python).
- You want a Kubernetes-native model serving platform.
- You want a cloud-agnostic framework.
- You want pre-built Docker images to get models in production.
- You want built-in model monitoring features.
- You need minimal code editing to start serving the model.
- You want integrated Nvidia NVIDIA Triton.
Watch out
- It is not suited for edge-based or IoT model serving.
- Running and maintaining Kubernetes clusters for model serving may not always be optimal.
Example stacks
Airflow + MLflow stack
Installation
kubectl create namespace seldon-system
helm install seldon-core seldon-core-operator --repo https://storage.googleapis.com/seldon-charts --set usageMetrics.enabled=true --namespace seldon-system --set istio.enabled=true