Updates artifacts for v1.2.0-rc.1 release

nirrozenbaum · nirrozenbaum · commit 318cd7ceab64 · 2025-11-21T15:22:24.000+02:00
Signed-off-by: Nir Rozenbaum &lt;nirro@il.ibm.com&gt;
diff --git a/config/charts/body-based-routing/values.yaml b/config/charts/body-based-routing/values.yaml
@@ -3,8 +3,8 @@ bbr:
   replicas: 1
   image:
     name: bbr
-    hub: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension
-    tag: main
+    hub: registry.k8s.io/gateway-api-inference-extension
+    tag: v1.2.0-rc.1
     pullPolicy: Always
   port: 9004
   healthCheckPort: 9005
diff --git a/config/charts/inferencepool/values.yaml b/config/charts/inferencepool/values.yaml
@@ -2,8 +2,8 @@ inferenceExtension:
   replicas: 1
   image:
     name: epp
-    hub: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension
-    tag: main
+    hub: registry.k8s.io/gateway-api-inference-extension
+    tag: v1.2.0-rc.1
     pullPolicy: Always
   extProcPort: 9002
   env: []
diff --git a/config/crd/bases/inference.networking.k8s.io_inferencepools.yaml b/config/crd/bases/inference.networking.k8s.io_inferencepools.yaml
@@ -3,7 +3,7 @@ kind: CustomResourceDefinition
 metadata:
   annotations:
     api-approved.kubernetes.io: https://github.com/kubernetes-sigs/gateway-api-inference-extension/pull/1173
-    inference.networking.k8s.io/bundle-version: main-dev
+    inference.networking.k8s.io/bundle-version: v1.2.0-rc.1
   name: inferencepools.inference.networking.k8s.io
 spec:
   group: inference.networking.k8s.io
diff --git a/config/crd/bases/inference.networking.x-k8s.io_inferencemodelrewrites.yaml b/config/crd/bases/inference.networking.x-k8s.io_inferencemodelrewrites.yaml
@@ -2,7 +2,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    inference.networking.k8s.io/bundle-version: main-dev
+    inference.networking.k8s.io/bundle-version: v1.2.0-rc.1
   name: inferencemodelrewrites.inference.networking.x-k8s.io
 spec:
   group: inference.networking.x-k8s.io
diff --git a/config/crd/bases/inference.networking.x-k8s.io_inferenceobjectives.yaml b/config/crd/bases/inference.networking.x-k8s.io_inferenceobjectives.yaml
@@ -2,7 +2,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    inference.networking.k8s.io/bundle-version: main-dev
+    inference.networking.k8s.io/bundle-version: v1.2.0-rc.1
   name: inferenceobjectives.inference.networking.x-k8s.io
 spec:
   group: inference.networking.x-k8s.io
diff --git a/config/crd/bases/inference.networking.x-k8s.io_inferencepoolimports.yaml b/config/crd/bases/inference.networking.x-k8s.io_inferencepoolimports.yaml
@@ -2,7 +2,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    inference.networking.k8s.io/bundle-version: main-dev
+    inference.networking.k8s.io/bundle-version: v1.2.0-rc.1
   name: inferencepoolimports.inference.networking.x-k8s.io
 spec:
   group: inference.networking.x-k8s.io
diff --git a/config/crd/bases/inference.networking.x-k8s.io_inferencepools.yaml b/config/crd/bases/inference.networking.x-k8s.io_inferencepools.yaml
@@ -3,7 +3,7 @@ kind: CustomResourceDefinition
 metadata:
   annotations:
     api-approved.kubernetes.io: unapproved, experimental-only
-    inference.networking.k8s.io/bundle-version: main-dev
+    inference.networking.k8s.io/bundle-version: v1.2.0-rc.1
   name: inferencepools.inference.networking.x-k8s.io
 spec:
   group: inference.networking.x-k8s.io
diff --git a/config/manifests/vllm/cpu-deployment.yaml b/config/manifests/vllm/cpu-deployment.yaml
@@ -14,8 +14,8 @@ spec:
     spec:
       containers:
         - name: lora
-          image: "public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v0.8.5" # formal images can be found in https://gallery.ecr.aws/q9t5s3a7/vllm-cpu-release-repo
-          imagePullPolicy: Always
+          image: "public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v0.9.3" # formal images can be found in https://gallery.ecr.aws/q9t5s3a7/vllm-cpu-release-repo
+          imagePullPolicy: IfNotPresent
           command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
           args:
           - "--model"
@@ -77,8 +77,8 @@ spec:
         - name: lora-adapter-syncer
           tty: true
           stdin: true
-          image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/lora-syncer:main
-          restartPolicy: Always
+          image: registry.k8s.io/gateway-api-inference-extension/lora-syncer:v1.2.0-rc.1
+          restartPolicy: IfNotPresent
           imagePullPolicy: Always
           env:
             - name: DYNAMIC_LORA_ROLLOUT_CONFIG
diff --git a/config/manifests/vllm/gpu-deployment.yaml b/config/manifests/vllm/gpu-deployment.yaml
@@ -15,7 +15,7 @@ spec:
       containers:
         - name: vllm
           image: "vllm/vllm-openai:v0.8.5"
-          imagePullPolicy: Always
+          imagePullPolicy: IfNotPresent
           command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
           args:
           - "--model"
@@ -155,8 +155,8 @@ spec:
         - name: lora-adapter-syncer
           tty: true
           stdin: true 
-          image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/lora-syncer:main
-          restartPolicy: Always
+          image: registry.k8s.io/gateway-api-inference-extension/lora-syncer:v1.2.0-rc.1
+          restartPolicy: IfNotPresent
           imagePullPolicy: Always
           env: 
             - name: DYNAMIC_LORA_ROLLOUT_CONFIG
diff --git a/config/manifests/vllm/sim-deployment.yaml b/config/manifests/vllm/sim-deployment.yaml
@@ -15,7 +15,7 @@ spec:
       containers:
       - name: vllm-sim
         image: ghcr.io/llm-d/llm-d-inference-sim:v0.5.0
-        imagePullPolicy: Always
+        imagePullPolicy: IfNotPresent
         args:
         - --model
         - meta-llama/Llama-3.1-8B-Instruct
diff --git a/conformance/resources/base.yaml b/conformance/resources/base.yaml
@@ -200,8 +200,8 @@ spec:
       terminationGracePeriodSeconds: 130
       containers:
       - name: epp
-        image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/epp:v20251105-cbb8928
-        imagePullPolicy: Always
+        image: registry.k8s.io/gateway-api-inference-extension/epp:v1.2.0-rc.1
+        imagePullPolicy: IfNotPresent
         args:
         - --pool-name
         - "primary-inference-pool"
@@ -298,8 +298,8 @@ spec:
       terminationGracePeriodSeconds: 130
       containers:
       - name: epp
-        image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/epp:v20251105-cbb8928
-        imagePullPolicy: Always
+        image: registry.k8s.io/gateway-api-inference-extension/epp:v1.2.0-rc.1
+        imagePullPolicy: IfNotPresent
         args:
         - --pool-name
         - "secondary-inference-pool"
@@ -507,8 +507,8 @@ spec:
       terminationGracePeriodSeconds: 130
       containers:
       - name: epp
-        image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/epp:v20251105-cbb8928
-        imagePullPolicy: Always
+        image: registry.k8s.io/gateway-api-inference-extension/epp:v1.2.0-rc.1
+        imagePullPolicy: IfNotPresent
         args:
         - --pool-name
         - "dp-inference-pool"
diff --git a/site-src/guides/index.md b/site-src/guides/index.md
@@ -18,25 +18,25 @@
 
     ```bash
     kubectl create secret generic hf-token --from-literal=token=$HF_TOKEN # Your Hugging Face Token with access to the set of Llama models
-    kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/vllm/gpu-deployment.yaml
+    kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/vllm/gpu-deployment.yaml
     ```
 
 --8<-- "site-src/_includes/model-server-cpu.md"
 
     ```bash
-    kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/vllm/cpu-deployment.yaml
+    kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/vllm/cpu-deployment.yaml
     ```
 
 --8<-- "site-src/_includes/model-server-sim.md"
 
     ```bash
-    kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/vllm/sim-deployment.yaml
+    kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/vllm/sim-deployment.yaml
     ```
 
 ### Install the Inference Extension CRDs
 
 ```bash
-kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.1.0/manifests.yaml
+kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.2.0-rc.1/manifests.yaml
 ```
 
 ### Install the Gateway
@@ -111,7 +111,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens
    Set the chart version and then select a tab to follow the provider-specific instructions.
 
    ```bash
-   export IGW_CHART_VERSION=v1.1.0
+   export IGW_CHART_VERSION=v1.2.0-rc.1
    ```
 
 --8<-- "site-src/_includes/epp.md"
@@ -129,7 +129,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens
       1. Deploy the Inference Gateway:
 
          ```bash
-         kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/gke/gateway.yaml
+         kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/gateway/gke/gateway.yaml
          ```
 
          Confirm that the Gateway was assigned an IP address and reports a `Programmed=True` status:
@@ -142,7 +142,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens
       1. Deploy the HTTPRoute:
 
          ```bash
-         kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/gke/httproute.yaml
+         kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/gateway/gke/httproute.yaml
          ```
 
       1. Confirm that the HTTPRoute status conditions include `Accepted=True` and `ResolvedRefs=True`:
@@ -191,7 +191,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens
       1. Deploy the Inference Gateway:
 
          ```bash
-         kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/agentgateway/gateway.yaml
+         kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/gateway/agentgateway/gateway.yaml
          ```
 
          Confirm that the Gateway was assigned an IP address and reports a `Programmed=True` status:
@@ -202,7 +202,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens
       1. Deploy the HTTPRoute:
 
          ```bash
-         kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/agentgateway/httproute.yaml
+         kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/gateway/agentgateway/httproute.yaml
          ```
 
       1. Confirm that the HTTPRoute status conditions include `Accepted=True` and `ResolvedRefs=True`:
@@ -267,7 +267,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens
 Deploy the sample InferenceObjective which allows you to specify priority of requests.
 
    ```bash
-   kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/inferenceobjective.yaml
+   kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/inferenceobjective.yaml
    ```
 
 --8<-- "site-src/_includes/test.md"
@@ -283,35 +283,35 @@ Deploy the sample InferenceObjective which allows you to specify priority of req
 
       ```bash
       helm uninstall vllm-llama3-8b-instruct
-      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/inferenceobjective.yaml --ignore-not-found
-      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/vllm/cpu-deployment.yaml --ignore-not-found
-      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/vllm/gpu-deployment.yaml --ignore-not-found
-      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/vllm/sim-deployment.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/inferenceobjective.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/vllm/cpu-deployment.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/vllm/gpu-deployment.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/vllm/sim-deployment.yaml --ignore-not-found
       kubectl delete secret hf-token --ignore-not-found
       ```
 
    1. Uninstall the Gateway API Inference Extension CRDs:
 
       ```bash
-      kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.1.0/manifests.yaml --ignore-not-found
+      kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.2.0-rc.1/manifests.yaml --ignore-not-found
       ```
       
    1. Choose one of the following options to cleanup the Inference Gateway.
 
 === "GKE"
 
       ```bash
-      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/gke/gateway.yaml --ignore-not-found
-      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/gke/healthcheck.yaml --ignore-not-found
-      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/gke/gcp-backend-policy.yaml --ignore-not-found
-      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/gke/httproute.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/gateway/gke/gateway.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/gateway/gke/healthcheck.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/gateway/gke/gcp-backend-policy.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/gateway/gke/httproute.yaml --ignore-not-found
       ```
 
 === "Istio"
 
       ```bash
-      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/istio/gateway.yaml --ignore-not-found
-      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/istio/httproute.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/gateway/istio/gateway.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/gateway/istio/httproute.yaml --ignore-not-found
       ```
 
       The following steps assume you would like to clean up ALL Istio resources that were created in this quickstart guide.
@@ -331,8 +331,8 @@ Deploy the sample InferenceObjective which allows you to specify priority of req
 === "Kgateway"
 
       ```bash
-      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/agentgateway/gateway.yaml --ignore-not-found
-      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/agentgateway/httproute.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/gateway/agentgateway/gateway.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0-rc.1/config/manifests/gateway/agentgateway/httproute.yaml --ignore-not-found
       ```
 
       The following steps assume you would like to cleanup ALL Kgateway resources that were created in this quickstart guide.
diff --git a/version/version.go b/version/version.go
@@ -30,5 +30,5 @@ const (
 	BundleVersionAnnotation = "inference.networking.k8s.io/bundle-version"
 
 	// BundleVersion is the value used for labeling the version of the gateway-api-inference-extension.
-	BundleVersion = "main-dev"
+	BundleVersion = "v1.2.0-rc.1"
 )
