fix helm chart support for gke v1alpha2.

Author: zetxqx

config/charts/inferencepool/README.md

@@ -131,6 +131,7 @@ The following table list the configurable parameters of the chart.
 
 | **Parameter Name**                          | **Description**                                                                                                        |
 |---------------------------------------------|------------------------------------------------------------------------------------------------------------------------|
+| `inferencePool.apiVersion`                  | The API version of the InferencePool resource. Defaults to `inference.networking.k8s.io/v1`. This can be changed to `inference.networking.x-k8s.io/v1alpha2` to support older API versions. |
 | `inferencePool.targetPortNumber`            | Target port number for the vllm backends, will be used to scrape metrics by the inference extension. Defaults to 8000. |
 | `inferencePool.modelServerType`            | Type of the model servers in the pool, valid options are [vllm, triton-tensorrt-llm], default is vllm. |
 | `inferencePool.modelServers.matchLabels`    | Label selector to match vllm backends managed by the inference pool.                                                   |

config/charts/inferencepool/templates/epp-deployment.yaml

@@ -27,6 +27,10 @@ spec:
         - {{ .Release.Name }}
         - --pool-namespace
         - {{ .Release.Namespace }}
+        {{- if ne .Values.inferencePool.apiVersion "inference.networking.k8s.io" }}
+        - --pool-group
+        - "{{ (split "/" .Values.inferencePool.apiVersion)._0 }}"
+        {{- end }}
         - --zap-encoder
         - "json"
         - --config-file

config/charts/inferencepool/templates/gke.yaml

@@ -9,7 +9,7 @@ metadata:
     {{- include "gateway-api-inference-extension.labels" . | nindent 4 }}
 spec:
   targetRef:
-    group: "inference.networking.k8s.io"
+    group: "{{ (split "/" .Values.inferencePool.apiVersion)._0 }}"
     kind: InferencePool
     name: {{ .Release.Name }}
   default:
@@ -28,7 +28,7 @@ metadata:
     {{- include "gateway-api-inference-extension.labels" . | nindent 4 }}
 spec:
   targetRef:
-    group: "inference.networking.k8s.io"
+    group: "{{ (split "/" .Values.inferencePool.apiVersion)._0 }}"
     kind: InferencePool
     name: {{ .Release.Name }}
   default:

config/charts/inferencepool/templates/rbac.yaml

@@ -40,9 +40,9 @@ metadata:
     {{- include "gateway-api-inference-extension.labels" . | nindent 4 }}
 rules:
 - apiGroups: ["inference.networking.x-k8s.io"]
-  resources: ["inferenceobjectives", "inferencepools"]
+  resources: ["inferenceobjectives"]
   verbs: ["get", "watch", "list"]
-- apiGroups: ["inference.networking.k8s.io"]
+- apiGroups: ["{{ (split "/" .Values.inferencePool.apiVersion)._0 }}"]
   resources: ["inferencepools"]
   verbs: ["get", "watch", "list"]
 - apiGroups: [""]