Kubeflow Inference Service Wizard
Deploy a model using for Kubeflow Inference Service
The KFService wizard is used if the user chooses a KFService after using the Create button
This differs from the SeldonDeployment wizard in its autoscaling options. A minimum and maximum number of pods can be set. This is in accordance with KFServing’s scaling based on knative, in response to the rate of requests.
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.
Last modified October 29, 2019: Reorganizing project structure and adding WIP image explanations (8bfc877)