feat: Change epp and conformance to use v1 type InferencePool (#1118)

* rename x-k8s to apix and add v1 InferencePool to api/v1

* changed epp and conformance test to support v1

* fixed duplicate import

* changed docker file

* updated docker file

* fixed naming collision

* added fake approved annotation

* try to fix unit tests

* fixed typo

* added annotation

* fixed annotation

* fixed integration test

* fixed e2e test

* change manifests

* added rbac

* Update api/v1/inferencepool_types.go

Co-authored-by: Rob Scott <[email protected]>

* Apply suggestions from code review

Co-authored-by: Rob Scott <[email protected]>

* use v1 type in v1alpha2

* clean unused depdendency

* fixed code generator error

* revert back

* merge bob's change

* upadted code-gen

* remove deep copy needs

* use codegen

* tried all alias

* push local changes

* changed inferencepoollist not to use v1.InferencePoolList

* changed comments

* fixed presubmit

* change to v1 ip

* revert to corev1 objectreference

* revert back to corev1 objectreference

* change crd

* remove crd

* manually add x-k8s.io inferencepool

* revert crd

* revert to workable version

* Revert "added rbac"

This reverts commit c01cbc8.

* run generator

* re-run generate

* revert to workable

* revert to workable version

* fixed test

* test

* revert it back to originall workable version

* change to use v1alpha2 back

* resolve merge conflicts

* fixed typo

* fixed typo

* fixed pipeline

* fixed boilerplate

Signed-off-by: Xiyue Yu <[email protected]>

* changed unused code

* fixed pipeline:

* fixed missing dependecny update

* updated missing dependency

* fixed imports

* fixed change

* fixed format

* merge to v1-inferencepool

* fixed integration test

* fixed import

* change to install scheme

* fixed import

* change back to main image

* fixed import issue

* fixed format

---------

Signed-off-by: Xiyue Yu <[email protected]>
Co-authored-by: Rob Scott <[email protected]>

Author: capri-xiyue

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
@@ -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
@@ -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