Update serving runtime version for 0.12 release and add some notes (#354

)

* Fix few bugs, add quick install failure note and update docs for release 0.12.0

Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>

* Add warning about control plane namespaces

Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>

* Resolve comments

Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>

---------

Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>

docs/admin/kubernetes_deployment.md

@@ -65,8 +65,7 @@ First in ConfigMap `inferenceservice-config` modify the `defaultDeploymentMode`
     kubectl patch configmap/inferenceservice-config -n kserve --type=strategic -p '{"data": {"deploy": "{\"defaultDeploymentMode\": \"RawDeployment\"}"}}'
     ```
 
-then modify the `ingressClassName` in `ingress` section to point to `IngressClass` name created in step 1.
-
+then modify the `ingressClassName` in `ingress` section to point to `IngressClass` name created in [step 1](#1-install-istio).
     ```yaml
     ingress: |-
     {

docs/get_started/README.md

@@ -16,7 +16,6 @@ The [Kubernetes CLI (`kubectl`)](https://kubernetes.io/docs/tasks/tools/install-
 
 ## Install the KServe "Quickstart" environment
 1. After having kind installed, create a `kind` cluster with:
-
     ```bash
     kind create cluster
     ```
@@ -38,6 +37,5 @@ The [Kubernetes CLI (`kubectl`)](https://kubernetes.io/docs/tasks/tools/install-
 3. You can then get started with a local deployment of KServe by using _KServe Quick installation script on Kind_:
 
     ```bash
-    curl -s "https://raw.githubusercontent.com/kserve/kserve/release-0.11/hack/quick_install.sh" | bash
+    curl -s "https://raw.githubusercontent.com/kserve/kserve/release-0.12/hack/quick_install.sh" | bash
     ```
-

docs/get_started/first_isvc.md

@@ -55,6 +55,10 @@ is provided as reference.
           storageUri: "gs://kfserving-examples/models/sklearn/1.0/model"
     EOF
     ```
+!!! Warning
+    Do not deploy `InferenceServices` in control plane namespaces (i.e. namespaces with `control-plane` label). The webhook is configured
+    in a way to skip these namespaces to avoid any privillage escalations. Deploying InferenceServices to these namespaces will result in the storage initializer not being 
+    injected into the pod, causing the pod to fail with the error `No such file or directory: '/mnt/models'`.
 
 ### 3. Check `InferenceService` status.