rename my-pool to vllm-llama2-7b

Author: ahg-g

config/manifests/inferencepool.yaml

@@ -2,22 +2,22 @@ apiVersion: inference.networking.x-k8s.io/v1alpha2
 kind: InferencePool
 metadata:
   labels:
-  name: my-pool
+  name: vllm-llama2-7b
 spec:
   targetPortNumber: 8000
   selector:
-    app: my-pool
+    app: vllm-llama2-7b
   extensionRef:
-    name: my-pool-epp
+    name: vllm-llama2-7b-epp
 ---
 apiVersion: v1
 kind: Service
 metadata:
-  name: my-pool-epp
+  name: vllm-llama2-7b-epp
   namespace: default
 spec:
   selector:
-    app: my-pool-epp
+    app: vllm-llama2-7b-epp
   ports:
     - protocol: TCP
       port: 9002
@@ -27,27 +27,27 @@ spec:
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: my-pool-epp
+  name: vllm-llama2-7b-epp
   namespace: default
   labels:
-    app: my-pool-epp
+    app: vllm-llama2-7b-epp
 spec:
   replicas: 1
   selector:
     matchLabels:
-      app: my-pool-epp
+      app: vllm-llama2-7b-epp
   template:
     metadata:
       labels:
-        app: my-pool-epp
+        app: vllm-llama2-7b-epp
     spec:
       containers:
       - name: epp
         image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/epp:main
         imagePullPolicy: Always
         args:
         - -poolName
-        - "my-pool"
+        - "vllm-llama2-7b"
         - -v
         - "4"
         - -grpcPort

config/manifests/vllm/cpu-deployment.yaml

@@ -1,16 +1,16 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: my-pool
+  name: vllm-llama2-7b
 spec:
   replicas: 3
   selector:
     matchLabels:
-      app: my-pool
+      app: vllm-llama2-7b
   template:
     metadata:
       labels:
-        app: my-pool
+        app: vllm-llama2-7b
     spec:
       containers:
         - name: lora

config/manifests/vllm/gpu-deployment.yaml

@@ -1,16 +1,16 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: my-pool
+  name: vllm-llama2-7b
 spec:
   replicas: 3
   selector:
     matchLabels:
-      app: my-pool
+      app: vllm-llama2-7b
   template:
     metadata:
       labels:
-        app: my-pool
+        app: vllm-llama2-7b
     spec:
       containers:
         - name: lora

test/e2e/epp/e2e_suite_test.go

@@ -57,15 +57,15 @@ const (
 	// TODO [danehans]: Must be "default" until https://github.com/kubernetes-sigs/gateway-api-inference-extension/issues/227 is fixed
 	nsName = "default"
 	// modelServerName is the name of the model server test resources.
-	modelServerName = "my-pool"
+	modelServerName = "vllm-llama2-7b"
 	// modelName is the test model name.
 	modelName = "tweet-summary"
 	// envoyName is the name of the envoy proxy test resources.
 	envoyName = "envoy"
 	// envoyPort is the listener port number of the test envoy proxy.
 	envoyPort = "8081"
 	// inferExtName is the name of the inference extension test resources.
-	inferExtName = "my-pool-epp"
+	inferExtName = "vllm-llama2-7b-epp"
 	// clientManifest is the manifest for the client test resources.
 	clientManifest = "../../testdata/client.yaml"
 	// modelServerSecretManifest is the manifest for the model server secret resource.

test/testdata/envoy.yaml

@@ -100,7 +100,7 @@ data:
                           grpc_service:
                             envoy_grpc:
                               cluster_name: ext_proc
-                              authority: my-pool-epp.default:9002
+                              authority: vllm-llama2-7b-epp.default:9002
                             timeout: 10s
                           processing_mode:
                             request_header_mode: SEND
@@ -194,7 +194,7 @@ data:
                   - endpoint:
                       address:
                         socket_address:
-                          address: my-pool-epp.default
+                          address: vllm-llama2-7b-epp.default
                           port_value: 9002
                     health_status: HEALTHY
                     load_balancing_weight: 1