Fix epp image and add placeholder docker repos for latency sidecars

Author: BenjaminBraunDev

cmd/epp/runner/runner.go

@@ -865,7 +865,11 @@ type predictorRunnable struct {
 
 func (p *predictorRunnable) Start(ctx context.Context) error {
 	setupLog.Info("Starting latency predictor...")
-	p.predictor.Start(ctx)
+	if err := p.predictor.Start(ctx); err != nil {
+		setupLog.Error(err, "Failed to start latency predictor")
+		return err
+	}
+	setupLog.Info("Latency predictor started.")
 	<-ctx.Done()
 	setupLog.Info("Stopping latency predictor...")
 	p.predictor.Stop()

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

@@ -46,6 +46,16 @@ data:
   {{- .Values.inferenceExtension.pluginsCustomConfig | toYaml | nindent 2 }}
   {{- end }}
 ---
+{{- if .Values.inferenceExtension.sidecar.enabled }}
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ .Values.inferenceExtension.sidecar.configMap.name }}
+  namespace: {{ .Release.Namespace }}
+data:
+  {{- .Values.inferenceExtension.sidecar.configMap.data | toYaml | nindent 2 }}
+{{- end }}
+---
 {{- if .Values.inferenceExtension.latencyPredictor.enabled }}
 apiVersion: v1
 kind: ConfigMap
@@ -55,7 +65,7 @@ metadata:
 data:
   {{- range $key, $value := .Values.inferenceExtension.latencyPredictor.trainingServer.config }}
   {{ $key }}: {{ $value | quote }}
-  {{- end }}
+{{- end }}
 ---
 apiVersion: v1
 kind: ConfigMap

config/charts/inferencepool/values.yaml

@@ -1,9 +1,9 @@
 inferenceExtension:
   replicas: 1
   image:
-    name: epp-wlp-latencypredictor-helm-v2
-    hub:  us-docker.pkg.dev/kaushikmitra-gke-dev/kaushikmitra-docker-repo
-    tag: latest
+    name: epp
+    hub: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension
+    tag: main
     pullPolicy: Always
   extProcPort: 9002
   env: []
@@ -12,6 +12,11 @@ inferenceExtension:
   extraContainerPorts: []
   # Define additional service ports
   extraServicePorts: []
+  #  extraServicePorts:
+  #    - name: http
+  #      port: 8081
+  #      protocol: TCP
+  #      targetPort: 8081
 
   # This is the plugins configuration file.
   # pluginsCustomConfig:
@@ -39,6 +44,10 @@ inferenceExtension:
 
   tolerations: []
 
+  # Sidecar configuration for EPP
+  sidecar:
+    enabled: false
+
   # Monitoring configuration for EPP
   monitoring:
     interval: "10s"
@@ -69,7 +78,7 @@ inferenceExtension:
     # Training Server Configuration
     trainingServer:
       image:
-        hub: us-docker.pkg.dev/kaushikmitra-gke-dev/kaushikmitra-docker-repo
+        hub: path/to/your/docker/repo # NOTE: Update with your Docker repository path for sidecars
         name: latencypredictor-v3-training-server
         tag: latest
         pullPolicy: Always
@@ -110,7 +119,7 @@ inferenceExtension:
       count: 10
       startPort: 8001
       image:
-        hub: us-docker.pkg.dev/kaushikmitra-gke-dev/kaushikmitra-docker-repo
+        hub: path/to/your/docker/repo # NOTE: Update with your Docker repository path for sidecars
         name: latencypredictor-v3-prediction-server
         tag: latest
         pullPolicy: Always
@@ -168,12 +177,25 @@ provider:
     # Set to true if the cluster is an Autopilot cluster.
     autopilot: false
 
+  # Istio-specific configuration.
+  # This block is only used if name is "istio".
+  istio:
+    destinationRule:
+      # Provide a way to override the default calculated host
+      host: ""
+      # Optional: Enables customization of the traffic policy
+      trafficPolicy: {}
+        # connectionPool:
+        #   http:
+        #     maxRequestsPerConnection: 256000
+
+# DEPRECATED and will be removed in v1.3. Instead, use `provider.istio.*`.
 istio:
   destinationRule:
     # Provide a way to override the default calculated host
-    host: "" 
+    host: ""
     # Optional: Enables customization of the traffic policy
     trafficPolicy: {}
       # connectionPool:
       #   http:
-      #     maxRequestsPerConnection: 256000
+      #     maxRequestsPerConnection: 256000