2085 Advanced model serving leveraging KFServing and Seldon on OpenShift

Model Inferencing use cases are becoming a requirement for models moving into the next phase of production deployments. Join us as we explore these using Kubeflow Serving (KFServing), Seldon and the native OpenShift stack. We’ll show how autoscaling, scale-to-zero, and canary deployments are implemented, including scenarios where traffic is optimized to the best performing models. We will also detail Red Hat Marketplace and Seldon integration, and how you can leverage it.