Updates artifacts for v1.2.0 release

Signed-off-by: Nir Rozenbaum <[email protected]>

Author: nirrozenbaum

config/charts/body-based-routing/values.yaml

@@ -4,7 +4,7 @@ bbr:
   image:
     name: bbr
     hub: registry.k8s.io/gateway-api-inference-extension
-    tag: v1.2.0-rc.1
+    tag: v1.2.0
     pullPolicy: Always
   port: 9004
   healthCheckPort: 9005

config/charts/inferencepool/values.yaml

@@ -3,7 +3,7 @@ inferenceExtension:
   image:
     name: epp
     hub: registry.k8s.io/gateway-api-inference-extension
-    tag: v1.2.0-rc.1
+    tag: v1.2.0
     pullPolicy: Always
   extProcPort: 9002
   env: []

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: v1.2.0-rc.1
+    inference.networking.k8s.io/bundle-version: v1.2.0
   name: inferencepools.inference.networking.k8s.io
 spec:
   group: inference.networking.k8s.io

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: v1.2.0-rc.1
+    inference.networking.k8s.io/bundle-version: v1.2.0
   name: inferencemodelrewrites.inference.networking.x-k8s.io
 spec:
   group: inference.networking.x-k8s.io

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: v1.2.0-rc.1
+    inference.networking.k8s.io/bundle-version: v1.2.0
   name: inferenceobjectives.inference.networking.x-k8s.io
 spec:
   group: inference.networking.x-k8s.io

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: v1.2.0-rc.1
+    inference.networking.k8s.io/bundle-version: v1.2.0
   name: inferencepoolimports.inference.networking.x-k8s.io
 spec:
   group: inference.networking.x-k8s.io

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: v1.2.0-rc.1
+    inference.networking.k8s.io/bundle-version: v1.2.0
   name: inferencepools.inference.networking.x-k8s.io
 spec:
   group: inference.networking.x-k8s.io

config/manifests/vllm/sim-deployment.yaml

@@ -14,7 +14,7 @@ spec:
     spec:
       containers:
       - name: vllm-sim
-        image: ghcr.io/llm-d/llm-d-inference-sim:v0.5.0
+        image: ghcr.io/llm-d/llm-d-inference-sim:v0.6.1
         imagePullPolicy: IfNotPresent
         args:
         - --model

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/v1.2.0-rc.1/config/manifests/vllm/gpu-deployment.yaml
+    kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/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/v1.2.0-rc.1/config/manifests/vllm/cpu-deployment.yaml
+    kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/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/v1.2.0-rc.1/config/manifests/vllm/sim-deployment.yaml
+    kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/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/v1.2.0-rc.1/manifests.yaml
+kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.2.0/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=v1.2.0-rc.1
+   export IGW_CHART_VERSION=v1.2.0
    ```
 
 --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/v1.2.0-rc.1/config/manifests/gateway/gke/gateway.yaml
+         kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/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/v1.2.0-rc.1/config/manifests/gateway/gke/httproute.yaml
+         kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/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/v1.2.0-rc.1/config/manifests/gateway/agentgateway/gateway.yaml
+         kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/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/v1.2.0-rc.1/config/manifests/gateway/agentgateway/httproute.yaml
+         kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/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/v1.2.0-rc.1/config/manifests/inferenceobjective.yaml
+   kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/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/v1.2.0-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 -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/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/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/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/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/v1.2.0-rc.1/manifests.yaml --ignore-not-found
+      kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.2.0/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/v1.2.0-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
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/config/manifests/gateway/gke/gateway.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/config/manifests/gateway/gke/healthcheck.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/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/v1.2.0/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/v1.2.0-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
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/config/manifests/gateway/istio/gateway.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/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/v1.2.0-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
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/config/manifests/gateway/agentgateway/gateway.yaml --ignore-not-found
+      kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.0/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.

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 = "v1.2.0-rc.1"
+	BundleVersion = "v1.2.0"
 )