Updates artifacts for v0.5.0-rc.1 release

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

Author: nirrozenbaum

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: v0.5.0-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: v0.5.0-rc.1
     pullPolicy: Always
   extProcPort: 9002
   env: {}

config/manifests/inferencepool-resources.yaml

@@ -48,8 +48,8 @@ spec:
       terminationGracePeriodSeconds: 130
       containers:
       - name: epp
-        image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/epp:main
-        imagePullPolicy: Always
+        image: registry.k8s.io/gateway-api-inference-extension/epp:v0.5.0-rc.1
+        imagePullPolicy: IfNotPresent
         args:
         - -poolName
         - "vllm-llama3-8b-instruct"

config/manifests/vllm/cpu-deployment.yaml

@@ -14,8 +14,8 @@ spec:
     spec:
       containers:
         - name: lora
-          image: "public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v0.9.1" # 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:v0.9.2" # 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"

config/manifests/vllm/gpu-deployment.yaml

@@ -14,8 +14,8 @@ spec:
     spec:
       containers:
         - name: vllm
-          image: "vllm/vllm-openai:latest"
-          imagePullPolicy: Always
+          image: "vllm/vllm-openai:v0.9.2"
+          imagePullPolicy: IfNotPresent
           command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
           args:
           - "--model"

config/manifests/vllm/sim-deployment.yaml

@@ -15,7 +15,7 @@ spec:
       containers:
       - name: vllm-sim
         image: ghcr.io/llm-d/llm-d-inference-sim:v0.1.2
-        imagePullPolicy: Always
+        imagePullPolicy: IfNotPresent
         args:
         - --model
         - meta-llama/Llama-3.1-8B-Instruct