RHOAIENG-28400 - Document on-off toggle for stop/start models (#881)

Author: eturner24

assemblies/serving-large-models.adoc

@@ -19,6 +19,7 @@ include::modules/enabling-the-single-model-serving-platform.adoc[leveloffset=+2]
 include::modules/adding-a-custom-model-serving-runtime-for-the-single-model-serving-platform.adoc[leveloffset=+2]
 include::modules/adding-a-tested-and-verified-runtime-for-the-single-model-serving-platform.adoc[leveloffset=+2]
 include::modules/deploying-models-on-the-single-model-serving-platform.adoc[leveloffset=+2]
+include::modules/stopping-starting-model.adoc[leveloffset=+2]
 include::modules/deploying-models-using-multiple-gpu-nodes.adoc[leveloffset=+2]
 include::modules/setting-timeout-for-kserve.adoc[leveloffset=+2]
 include::modules/customizing-parameters-serving-runtime.adoc[leveloffset=+2]

modules/customizing-parameters-serving-runtime.adoc

@@ -16,15 +16,17 @@ NOTE: Customizing the parameters of a runtime only affects the selected model de
 . From the {productname-short} dashboard, click *Models* -> *Model deployments*. 
 +
 The *Model deployments* page opens.
-. Click the action menu (⋮) next to the name of the model you want to customize and select *Edit*.
+. Click *Stop* next to the name of the model you want to customize. 
+. Click the action menu (⋮) and select *Edit*.
 +
 The *Configuration parameters* section shows predefined serving runtime parameters, if any are available.
 . Customize the runtime parameters in the *Configuration parameters* section:
 .. Modify the values in *Additional serving runtime arguments* to define how the deployed model behaves.
 .. Modify the values in *Additional environment variables* to define variables in the model's environment.
 +
 NOTE: Do not modify the port or model serving runtime arguments, because they require specific values to be set. Overwriting these parameters can cause the deployment to fail.
-. After you are done customizing the runtime parameters, click *Redeploy* to save and deploy the model with your changes.
+. After you are done customizing the runtime parameters, click *Redeploy* to save.
+. Click *Start* to deploy the model with your changes.
 
 .Verification
 * Confirm that the deployed model is shown on the *Models* tab for the project, and on the *Model deployments* page of the dashboard with a checkmark in the *Status* column.

modules/stopping-starting-model.adoc

@@ -0,0 +1,19 @@
+:_module-type: PROCEDURE
+
+[id="stopping-starting-model_{context}"]
+= Stopping and starting a deployed model
+
+[role='_abstract']
+You can stop a deployed model to perform edits without consuming cluster resources or triggering a redeployment. When you stop a model, all associated objects are terminated, and the model is unavailable for inference requests. When you start the model again, any pending configuration changes are applied.
+
+.Prerequisites
+* You have logged in to {productname-long}.
+* You have deployed a model in a data science project.
+
+.Procedure   
+
+. From the {productname-short} dashboard, click *Models* > *Model deployments*.
+. Locate the model that you want to stop or start.
+. In the *Status* column for the model, click *Stop* or *Start*.
++
+When you stop the model, the status changes to *Stopping* as the pods are terminated, and then changes to *Stopped*. When you start the model, the status changes to *Starting* as new pods are created, and then changes to *Running*.