move autopilot to provider.gke.

Author: zetxqx

config/charts/inferencepool/README.md

@@ -135,6 +135,8 @@ inferenceExtension:
 
 For GKE environments, monitoring is enabled by setting `provider.name` to `gke` and `inferenceExtension.monitoring.gke.enabled` to `true`. This will create the necessary `PodMonitoring` and RBAC resources for metrics collection.
 
+If you are using a GKE Autopilot cluster, you also need to set `provider.gke.autopilot` to `true`.
+
 Then apply it with:
 
 ```txt
@@ -174,10 +176,10 @@ The following table list the configurable parameters of the chart.
 | `inferenceExtension.monitoring.interval`   | Metrics scraping interval for monitoring. Defaults to `10s`.                                                           |
 | `inferenceExtension.monitoring.secret.name` | Name of the service account token secret for metrics authentication. Defaults to `inference-gateway-sa-metrics-reader-secret`. |
 | `inferenceExtension.monitoring.prometheus.enabled` | Enable Prometheus ServiceMonitor creation for EPP metrics collection. Defaults to `false`.                      |
-| `inferenceExtension.monitoring.gke.enabled` | Enable GKE monitoring resources (`PodMonitoring` and RBAC). Defaults to `false`.                      |
-| `inferenceExtension.monitoring.gke.autopilot` | Set to `true` if the cluster is a GKE Autopilot cluster. This ensures the correct `gke-gmp-system` namespace is used for the GMP collector. Defaults to `false`. |
+| `inferenceExtension.monitoring.gke.enabled` | Enable GKE monitoring resources (`PodMonitoring` and RBAC). Defaults to `false`. |
 | `inferenceExtension.pluginsCustomConfig`    | Custom config that is passed to EPP as inline yaml.      |
 | `provider.name`                             | Name of the Inference Gateway implementation being used. Possible values: `gke`. Defaults to `none`.                   |
+| `provider.gke.autopilot` | Set to `true` if the cluster is a GKE Autopilot cluster. This is only used if `provider.name` is `gke`. Defaults to `false`. |
 
 ## Notes
 

config/charts/inferencepool/templates/gke.yaml

@@ -42,7 +42,11 @@ spec:
 {{- $metricsReadRoleBindingName := printf "%s-%s-metrics-reader-role-binding" .Release.Namespace .Release.Name -}}
 {{- $secretReadRoleName := printf "%s-metrics-reader-secret-read" .Release.Name -}}
 {{- $gmpNamespace := "gmp-system" -}}
-{{- if .Values.inferenceExtension.monitoring.gke.autopilot -}}
+{{- $isAutopilot := false -}}
+{{- with .Values.provider.gke }}
+  {{- $isAutopilot = .autopilot | default false -}}
+{{- end }}
+{{- if $isAutopilot -}}
 {{-   $gmpNamespace = "gke-gmp-system" -}}
 {{- end -}}
 {{- $gmpCollectorRoleBindingName := printf "%s:collector:%s-%s-metrics-reader-secret-read" $gmpNamespace .Release.Namespace .Release.Name -}}

config/charts/inferencepool/values.yaml

@@ -53,8 +53,6 @@ inferenceExtension:
 
     gke:
       enabled: false
-      # Set to true if the cluster is an Autopilot cluster.
-      autopilot: false
 
 inferencePool:
   targetPorts:
@@ -72,3 +70,8 @@ inferencePool:
 provider:
   name: none
 
+  # GKE-specific configuration.
+  # This block is only used if name is "gke".
+  gke:
+    # Set to true if the cluster is an Autopilot cluster.
+    autopilot: false