update whole repo to v1 inferencepool (#1213)

Author: capri-xiyue

Makefile

@@ -292,6 +292,14 @@ live-docs:
 	docker build -t gaie/mkdocs hack/mkdocs/image
 	docker run --rm -it -p 3000:3000 -v ${PWD}:/docs gaie/mkdocs
 
+.PHONY: apix-ref-docs
+apix-ref-docs:
+	crd-ref-docs \
+		--source-path=${PWD}/apix/v1alpha2 \
+		--config=crd-ref-docs.yaml \
+		--renderer=markdown \
+		--output-path=${PWD}/site-src/reference/x-spec.md
+
 .PHONY: api-ref-docs
 api-ref-docs:
 	crd-ref-docs \

config/charts/inferencepool/templates/gke.yaml

@@ -9,7 +9,7 @@ metadata:
     {{- include "gateway-api-inference-extension.labels" . | nindent 4 }}
 spec:
   targetRef:
-    group: "inference.networking.x-k8s.io"
+    group: "inference.networking.k8s.io"
     kind: InferencePool
     name: {{ .Release.Name }}
   default:
@@ -28,7 +28,7 @@ metadata:
     {{- include "gateway-api-inference-extension.labels" . | nindent 4 }}
 spec:
   targetRef:
-    group: "inference.networking.x-k8s.io"
+    group: "inference.networking.k8s.io"
     kind: InferencePool
     name: {{ .Release.Name }}
   default:

config/charts/inferencepool/templates/inferencepool.yaml

@@ -1,5 +1,5 @@
 {{ include "gateway-api-inference-extension.validations.inferencepool.common" $ }}
-apiVersion: inference.networking.x-k8s.io/v1alpha2
+apiVersion: inference.networking.k8s.io/v1
 kind: InferencePool
 metadata:
   name: {{ .Release.Name }}

config/charts/inferencepool/templates/rbac.yaml

@@ -8,6 +8,9 @@ rules:
 - apiGroups: ["inference.networking.x-k8s.io"]
   resources: ["inferencemodels", "inferencepools"]
   verbs: ["get", "watch", "list"]
+- apiGroups: ["inference.networking.k8s.io"]
+  resources: ["inferencepools"]
+  verbs: ["get", "watch", "list"]
 - apiGroups: [""]
   resources: ["pods"]
   verbs: ["get", "watch", "list"]

config/manifests/gateway/gke/gcp-backend-policy.yaml

@@ -4,7 +4,7 @@ metadata:
   name: inferencepool-backend-policy
 spec:
   targetRef:
-    group: "inference.networking.x-k8s.io"
+    group: "inference.networking.k8s.io"
     kind: InferencePool
     name: vllm-llama3-8b-instruct
   default:

config/manifests/inferencepool-resources.yaml

@@ -3,7 +3,7 @@
 #  - ./conformance/resources/manifests/manifests.yaml
 #  - ./site-src/guides/inferencepool-rollout.md
 ---
-apiVersion: inference.networking.x-k8s.io/v1alpha2
+apiVersion: inference.networking.k8s.io/v1
 kind: InferencePool
 metadata:
   name: vllm-llama3-8b-instruct

site-src/api-types/inferencepool.md

@@ -28,7 +28,7 @@ In summary, the InferencePoolSpec consists of 3 major parts:
 Here is an example InferencePool configuration:
 
 ```
-apiVersion: inference.networking.x-k8s.io/v1alpha2
+apiVersion: inference.networking.k8s.io/v1
 kind: InferencePool
 metadata:
   name: vllm-llama3-8b-instruct

site-src/guides/implementers.md

@@ -22,7 +22,7 @@ spec:
     name: inference-gateway
   rules:
   - backendRefs:
-    - group: inference.networking.x-k8s.io
+    - group: inference.networking.k8s.io
       kind: InferencePool
       name: base-model
     matches:
@@ -42,7 +42,7 @@ The general idea of implementing a Gateway controller supporting the InferencePo
 ### Endpoint Tracking
 Consider a simple inference pool like this:
 ```
-apiVersion: inference.networking.x-k8s.io/v1alpha2
+apiVersion: inference.networking.k8s.io/v1
 kind: InferencePool
 metadata:
   name: vllm-llama3-8b-instruct

site-src/guides/inferencepool-rollout.md

@@ -204,7 +204,7 @@ data:
         - id: food-review-1
           source: Kawon/llama3.1-food-finetune_v14_r8
 ---
-apiVersion: inference.networking.x-k8s.io/v1alpha2
+apiVersion: inference.networking.k8s.io/v1
 kind: InferencePool
 metadata:
   name: vllm-llama3-8b-instruct-new
@@ -400,11 +400,11 @@ spec:
       name: inference-gateway
   rules:
     - backendRefs:
-        - group: inference.networking.x-k8s.io
+        - group: inference.networking.k8s.io
           kind: InferencePool
           name: vllm-llama3-8b-instruct
           weight: 90
-        - group: inference.networking.x-k8s.io
+        - group: inference.networking.k8s.io
           kind: InferencePool
           name: vllm-llama3-8b-instruct-new
           weight: 10
@@ -448,7 +448,7 @@ spec:
       name: inference-gateway
   rules:
     - backendRefs:
-        - group: inference.networking.x-k8s.io
+        - group: inference.networking.k8s.io
           kind: InferencePool
           name: vllm-llama3-8b-instruct-new
           weight: 100