Deploying a model on a multi-model server
OpenShift AI multi-model servers can host several models at once. You create a new model server and deploy your model to it.
-
A user with
admin
privileges has enabled the multi-model serving platform on your OpenShift cluster.
-
In the OpenShift AI dashboard, navigate to the project details page and click the Models tab.
-
In the Multi-model serving platform tile, click Add model server.
-
In the form, provide the following values:
-
For Model server name, type a name, for example
Model Server
. -
For Serving runtime, select
OpenVINO Model Server
. -
Leave the other fields with the default settings.
-
-
Click Add.
-
In the Models and model servers list, next to the new model server, click Deploy model.
-
In the form, provide the following values:
-
For Model Name, type
fraud
. -
For Model framework, select
onnx-1
. -
For Existing data connection, select
My Storage
. -
Type the path that leads to the version folder that contains your model file:
models/fraud
-
Leave the other fields with the default settings.
-
-
Click Deploy.
Wait for the model to deploy and for the Status to show a green checkmark.