v1 epp

conformance/conformance.go

@@ -62,6 +62,7 @@ import (
 	// _ "sigs.k8s.io/gateway-api-inference-extension/conformance/tests/model_routing"
 
 	// Import the Inference Extension API types
+	inferencev1 "sigs.k8s.io/gateway-api-inference-extension/api/v1"
 	inferencev1alpha2 "sigs.k8s.io/gateway-api-inference-extension/apix/v1alpha2"
 	inferenceconfig "sigs.k8s.io/gateway-api-inference-extension/conformance/utils/config"
 )
@@ -132,6 +133,8 @@ func DefaultOptions(t *testing.T) confsuite.ConformanceOptions {
 	// Register Inference Extension API types
 	t.Logf("Attempting to install inferencev1alpha2 types into scheme from package: %s", inferencev1alpha2.GroupName)
 	require.NoError(t, inferencev1alpha2.Install(scheme), "failed to install inferencev1alpha2 types into scheme")
+	t.Logf("Attempting to install inferencev1 types into scheme from package: %s", inferencev1.GroupName)
+	require.NoError(t, inferencev1.Install(scheme), "failed to install inferencev1 types into scheme")
 
 	clientOptions := client.Options{Scheme: scheme}
 	c, err := client.New(cfg, clientOptions)

conformance/resources/manifests/manifests.yaml

@@ -146,7 +146,7 @@ spec:
               fieldPath: status.podIP
 ---
 # --- Primary InferencePool Definition ---
-apiVersion: inference.networking.x-k8s.io/v1alpha2
+apiVersion: inference.networking.k8s.io/v1
 kind: InferencePool
 metadata:
   name: primary-inference-pool
@@ -196,7 +196,7 @@ spec:
       terminationGracePeriodSeconds: 130
       containers:
       - name: epp
-        image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/epp:main
+        image: us-west1-docker.pkg.dev/xiyue-gke-dev-new/k8s-dev-images/epp:f1f87e9
         imagePullPolicy: Always
         args:
         - -poolName
@@ -239,7 +239,7 @@ spec:
           name: plugins-config
 ---
 # --- Secondary InferencePool Definition ---
-apiVersion: inference.networking.x-k8s.io/v1alpha2
+apiVersion: inference.networking.k8s.io/v1
 kind: InferencePool
 metadata:
   name: secondary-inference-pool
@@ -290,7 +290,7 @@ spec:
       terminationGracePeriodSeconds: 130
       containers:
       - name: epp
-        image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/epp:main
+        image: us-west1-docker.pkg.dev/xiyue-gke-dev-new/k8s-dev-images/epp:f1f87e9
         imagePullPolicy: Always
         args:
         - -poolName
@@ -363,6 +363,9 @@ rules:
 - apiGroups: ["inference.networking.x-k8s.io"]
   resources: ["inferencemodels", "inferencepools"]
   verbs: ["get", "list", "watch"]
+- apiGroups: ["inference.networking.k8s.io"]
+  resources: ["inferencepools"]
+  verbs: ["get", "list", "watch"]
 - apiGroups: [""]
   resources: ["pods"]
   verbs: ["get", "list", "watch"]

conformance/tests/basic/epp_unavailable_fail_open.yaml

@@ -27,7 +27,7 @@ spec:
   - "secondary.example.com"
   rules:
   - backendRefs:
-    - group: inference.networking.x-k8s.io
+    - group: inference.networking.k8s.io
       kind: InferencePool
       name: secondary-inference-pool # Use secondary-inferencePool because it has failureMode set to failOpen
     matches:

conformance/tests/basic/gateway_following_epp_routing.yaml

@@ -28,7 +28,7 @@ spec:
   - "primary.example.com"
   rules:
   - backendRefs:
-    - group: inference.networking.x-k8s.io
+    - group: inference.networking.k8s.io
       kind: InferencePool
       name: primary-inference-pool
     matches:

conformance/tests/basic/httproute_invalid_inferencepool_ref.yaml

@@ -21,7 +21,7 @@ spec:
     sectionName: http
   rules:
   - backendRefs:
-    - group: inference.networking.x-k8s.io
+    - group: inference.networking.k8s.io
       kind: InferencePool
       name: non-existent-inference-pool # Intentionally Non-Existing
     matches:

conformance/tests/basic/httproute_multiple_gateways_different_pools.yaml

@@ -13,7 +13,7 @@ spec:
   - "primary.example.com"
   rules:
   - backendRefs:
-    - group: inference.networking.x-k8s.io
+    - group: inference.networking.k8s.io
       kind: InferencePool
       name: primary-inference-pool
     matches:
@@ -35,7 +35,7 @@ spec:
   - "secondary.example.com"
   rules:
   - backendRefs:
-    - group: inference.networking.x-k8s.io
+    - group: inference.networking.k8s.io
       kind: InferencePool
       name: secondary-inference-pool
     matches:

conformance/tests/basic/inferencepool_accepted.yaml

@@ -13,7 +13,7 @@ spec:
     sectionName: http
   rules:
   - backendRefs:
-    - group: inference.networking.x-k8s.io # InferencePool API group
+    - group: inference.networking.k8s.io # InferencePool API group
       kind: InferencePool
       name: primary-inference-pool # Name of the InferencePool this route points to
       # namespace: gateway-conformance-app-backend - is omitted since it is in the same namespace as HTTPRoute

conformance/tests/basic/inferencepool_httproute_port_validation.yaml

@@ -16,7 +16,7 @@ spec:
   - "port-unspecified.example.com"
   rules:
   - backendRefs:
-    - group: inference.networking.x-k8s.io
+    - group: inference.networking.k8s.io
       kind: InferencePool
       name: primary-inference-pool
       # Port is intentionally unspecified here
@@ -42,7 +42,7 @@ spec:
   - "port-matching.example.com"
   rules:
   - backendRefs:
-    - group: inference.networking.x-k8s.io
+    - group: inference.networking.k8s.io
       kind: InferencePool
       name: primary-inference-pool
       port: 3000 # Port matches InferencePool's targetPortNumber
@@ -68,7 +68,7 @@ spec:
   - "port-non-matching.example.com"
   rules:
   - backendRefs:
-    - group: inference.networking.x-k8s.io
+    - group: inference.networking.k8s.io
       kind: InferencePool
       name: primary-inference-pool
       port: 8888 # Port does NOT match InferencePool's targetPortNumber

conformance/tests/basic/inferencepool_invalid_epp_service.go

@@ -21,7 +21,7 @@ import (
 
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/types"
-	inferenceapi "sigs.k8s.io/gateway-api-inference-extension/apix/v1alpha2"
+	inferenceapi "sigs.k8s.io/gateway-api-inference-extension/api/v1"
 	gatewayv1 "sigs.k8s.io/gateway-api/apis/v1"
 	"sigs.k8s.io/gateway-api/conformance/utils/kubernetes"
 	"sigs.k8s.io/gateway-api/conformance/utils/suite"

conformance/tests/basic/inferencepool_invalid_epp_service.yaml

@@ -1,4 +1,4 @@
-apiVersion: inference.networking.x-k8s.io/v1alpha2
+apiVersion: inference.networking.k8s.io/v1
 kind: InferencePool
 metadata:
   name: pool-with-invalid-epp
@@ -23,7 +23,7 @@ spec:
   - backendRefs:
     - name: pool-with-invalid-epp
       kind: InferencePool
-      group: inference.networking.x-k8s.io
+      group: inference.networking.k8s.io
     matches:
     - path:
         type: PathPrefix

conformance/tests/basic/inferencepool_multiple_rules_different_pools.yaml

@@ -16,12 +16,12 @@ spec:
       backendRefs:
         - name: primary-inference-pool
           kind: InferencePool
-          group: inference.networking.x-k8s.io
+          group: inference.networking.k8s.io
     - matches:
         - path:
             type: PathPrefix
             value: /secondary
       backendRefs:
         - name: secondary-inference-pool
           kind: InferencePool
-          group: inference.networking.x-k8s.io
+          group: inference.networking.k8s.io

conformance/tests/basic/inferencepool_resolvedrefs_condition.yaml

@@ -20,7 +20,7 @@ spec:
   - "primary.example.com"
   rules:
   - backendRefs:
-    - group: inference.networking.x-k8s.io
+    - group: inference.networking.k8s.io
       kind: InferencePool
       name: primary-inference-pool
     matches:
@@ -45,7 +45,7 @@ spec:
   - "secondary.example.com"
   rules:
   - backendRefs:
-    - group: inference.networking.x-k8s.io
+    - group: inference.networking.k8s.io
       kind: InferencePool
       name: primary-inference-pool
     matches:

conformance/utils/kubernetes/helpers.go

@@ -34,7 +34,7 @@ import (
 	"k8s.io/apimachinery/pkg/util/wait"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 
-	inferenceapi "sigs.k8s.io/gateway-api-inference-extension/apix/v1alpha2"
+	inferenceapi "sigs.k8s.io/gateway-api-inference-extension/api/v1"
 	"sigs.k8s.io/gateway-api-inference-extension/conformance/utils/config"
 	gatewayv1 "sigs.k8s.io/gateway-api/apis/v1"
 	gatewayapiconfig "sigs.k8s.io/gateway-api/conformance/utils/config"

pkg/epp/backend/metrics/logger.go

@@ -23,7 +23,7 @@ import (
 
 	"github.com/go-logr/logr"
 	"sigs.k8s.io/controller-runtime/pkg/log"
-	"sigs.k8s.io/gateway-api-inference-extension/apix/v1alpha2"
+	v1 "sigs.k8s.io/gateway-api-inference-extension/api/v1"
 	"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/metrics"
 	logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
 )
@@ -36,7 +36,7 @@ const (
 )
 
 type Datastore interface {
-	PoolGet() (*v1alpha2.InferencePool, error)
+	PoolGet() (*v1.InferencePool, error)
 	// PodMetrics operations
 	// PodGetAll returns all pods and metrics, including fresh and stale.
 	PodGetAll() []PodMetrics

pkg/epp/backend/metrics/pod_metrics_test.go

@@ -26,7 +26,7 @@ import (
 	corev1 "k8s.io/api/core/v1"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/types"
-	"sigs.k8s.io/gateway-api-inference-extension/apix/v1alpha2"
+	v1 "sigs.k8s.io/gateway-api-inference-extension/api/v1"
 )
 
 var (
@@ -86,8 +86,8 @@ func TestMetricsRefresh(t *testing.T) {
 
 type fakeDataStore struct{}
 
-func (f *fakeDataStore) PoolGet() (*v1alpha2.InferencePool, error) {
-	return &v1alpha2.InferencePool{Spec: v1alpha2.InferencePoolSpec{TargetPortNumber: 8000}}, nil
+func (f *fakeDataStore) PoolGet() (*v1.InferencePool, error) {
+	return &v1.InferencePool{Spec: v1.InferencePoolSpec{TargetPortNumber: 8000}}, nil
 }
 func (f *fakeDataStore) PodGetAll() []PodMetrics {
 	// Not implemented.

pkg/epp/controller/inferencemodel_reconciler_test.go

@@ -30,6 +30,7 @@ import (
 	ctrl "sigs.k8s.io/controller-runtime"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 	"sigs.k8s.io/controller-runtime/pkg/client/fake"
+	v1 "sigs.k8s.io/gateway-api-inference-extension/api/v1"
 	"sigs.k8s.io/gateway-api-inference-extension/apix/v1alpha2"
 	backendmetrics "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/backend/metrics"
 	"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
@@ -181,6 +182,7 @@ func TestInferenceModelReconciler(t *testing.T) {
 			scheme := runtime.NewScheme()
 			_ = clientgoscheme.AddToScheme(scheme)
 			_ = v1alpha2.Install(scheme)
+			_ = v1.Install(scheme)
 			initObjs := []client.Object{}
 			if test.model != nil {
 				initObjs = append(initObjs, test.model)

pkg/epp/controller/inferencepool_reconciler.go

@@ -24,7 +24,7 @@ import (
 	ctrl "sigs.k8s.io/controller-runtime"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 	"sigs.k8s.io/controller-runtime/pkg/log"
-	"sigs.k8s.io/gateway-api-inference-extension/apix/v1alpha2"
+	v1 "sigs.k8s.io/gateway-api-inference-extension/api/v1"
 	"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
 	logutil "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
 )
@@ -44,7 +44,7 @@ func (c *InferencePoolReconciler) Reconcile(ctx context.Context, req ctrl.Reques
 
 	logger.Info("Reconciling InferencePool")
 
-	infPool := &v1alpha2.InferencePool{}
+	infPool := &v1.InferencePool{}
 
 	if err := c.Get(ctx, req.NamespacedName, infPool); err != nil {
 		if errors.IsNotFound(err) {
@@ -70,6 +70,6 @@ func (c *InferencePoolReconciler) Reconcile(ctx context.Context, req ctrl.Reques
 
 func (c *InferencePoolReconciler) SetupWithManager(mgr ctrl.Manager) error {
 	return ctrl.NewControllerManagedBy(mgr).
-		For(&v1alpha2.InferencePool{}).
+		For(&v1.InferencePool{}).
 		Complete(c)
 }

pkg/epp/controller/inferencepool_reconciler_test.go

@@ -21,6 +21,9 @@ import (
 	"testing"
 	"time"
 
+	v1 "sigs.k8s.io/gateway-api-inference-extension/api/v1"
+	"sigs.k8s.io/gateway-api-inference-extension/apix/v1alpha2"
+
 	"github.com/google/go-cmp/cmp"
 	"github.com/google/go-cmp/cmp/cmpopts"
 	corev1 "k8s.io/api/core/v1"
@@ -30,7 +33,6 @@ import (
 	ctrl "sigs.k8s.io/controller-runtime"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 	"sigs.k8s.io/controller-runtime/pkg/client/fake"
-	"sigs.k8s.io/gateway-api-inference-extension/apix/v1alpha2"
 	backendmetrics "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/backend/metrics"
 	"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/datastore"
 	utiltest "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/testing"
@@ -78,6 +80,7 @@ func TestInferencePoolReconciler(t *testing.T) {
 	scheme := runtime.NewScheme()
 	_ = clientgoscheme.AddToScheme(scheme)
 	_ = v1alpha2.Install(scheme)
+	_ = v1.Install(scheme)
 
 	// Create a fake client with the pool and the pods.
 	initialObjects := []client.Object{pool1, pool2}
@@ -106,11 +109,11 @@ func TestInferencePoolReconciler(t *testing.T) {
 		t.Errorf("Unexpected diff (+got/-want): %s", diff)
 	}
 
-	newPool1 := &v1alpha2.InferencePool{}
+	newPool1 := &v1.InferencePool{}
 	if err := fakeClient.Get(ctx, req.NamespacedName, newPool1); err != nil {
 		t.Errorf("Unexpected pool get error: %v", err)
 	}
-	newPool1.Spec.Selector = map[v1alpha2.LabelKey]v1alpha2.LabelValue{"app": "vllm_v2"}
+	newPool1.Spec.Selector = map[v1.LabelKey]v1.LabelValue{"app": "vllm_v2"}
 	if err := fakeClient.Update(ctx, newPool1, &client.UpdateOptions{}); err != nil {
 		t.Errorf("Unexpected pool update error: %v", err)
 	}
@@ -153,7 +156,7 @@ func TestInferencePoolReconciler(t *testing.T) {
 }
 
 type diffStoreParams struct {
-	wantPool   *v1alpha2.InferencePool
+	wantPool   *v1.InferencePool
 	wantPods   []string
 	wantModels []*v1alpha2.InferenceModel
 }