Updates artifacts for v1.1.0-rc.1 release

Signed-off-by: Kellen Swain <[email protected]>

Author: kfswain

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: v1.1.0-rc.1
     pullPolicy: Always
   port: 9004
   healthCheckPort: 9005

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: v1.1.0-rc.1
     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: main-dev
+    inference.networking.k8s.io/bundle-version: v1.1.0-rc.1
   name: inferencepools.inference.networking.k8s.io
 spec:
   group: inference.networking.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: main-dev
+    inference.networking.k8s.io/bundle-version: v1.1.0-rc.1
   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: main-dev
+    inference.networking.k8s.io/bundle-version: v1.1.0-rc.1
   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: main-dev
+    inference.networking.k8s.io/bundle-version: v1.1.0-rc.1
   name: inferencepools.inference.networking.x-k8s.io
 spec:
   group: inference.networking.x-k8s.io

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:v1.1.0-rc.1
+          restartPolicy: IfNotPresent
           imagePullPolicy: Always
           env:
             - name: DYNAMIC_LORA_ROLLOUT_CONFIG

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:v1.1.0-rc.1
+          restartPolicy: IfNotPresent
           imagePullPolicy: Always
           env: 
             - name: DYNAMIC_LORA_ROLLOUT_CONFIG

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

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:v1.0.0
-        imagePullPolicy: Always
+        image: registry.k8s.io/gateway-api-inference-extension/epp:v1.1.0-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:v1.0.0
-        imagePullPolicy: Always
+        image: registry.k8s.io/gateway-api-inference-extension/epp:v1.1.0-rc.1
+        imagePullPolicy: IfNotPresent
         args:
         - --pool-name
         - "secondary-inference-pool"