diff --git a/config/manifests/gateway/extension_policy.yaml b/config/manifests/gateway/extension_policy.yaml
deleted file mode 100644
index 14b7b123c..000000000
--- a/config/manifests/gateway/extension_policy.yaml
+++ /dev/null
@@ -1,32 +0,0 @@
-apiVersion: gateway.envoyproxy.io/v1alpha1
-kind: EnvoyExtensionPolicy
-metadata:
-  name: ext-proc-policy
-  namespace: default
-spec:
-  extProc:
-    - backendRefs:
-      - group: ""
-        kind: Service
-        name: inference-gateway-ext-proc
-        port: 9002
-      processingMode:
-        allowModeOverride: true
-        request:
-          body: Buffered
-        response:
-      # The timeouts are likely not needed here. We can experiment with removing/tuning them slowly.
-      # The connection limits are more important and will cause the opaque: ext_proc_gRPC_error_14 error in Envoy GW if not configured correctly. 
-      messageTimeout: 1000s
-      backendSettings:
-        circuitBreaker:
-          maxConnections: 40000
-          maxPendingRequests: 40000
-          maxParallelRequests: 40000
-        timeout:
-          tcp:
-            connectTimeout: 24h
-  targetRef:
-    group: gateway.networking.k8s.io
-    kind: HTTPRoute
-    name: llm-route
diff --git a/config/manifests/inferencemodel.yaml b/config/manifests/inferencemodel.yaml
index 8374c5b3e..4c7824ca3 100644
--- a/config/manifests/inferencemodel.yaml
+++ b/config/manifests/inferencemodel.yaml
@@ -6,7 +6,7 @@ spec:
   modelName: tweet-summary
   criticality: Critical
   poolRef:
-    name: my-pool
+    name: vllm-llama2-7b
   targetModels:
   - name: tweet-summary-1
     weight: 100
@@ -20,7 +20,7 @@ spec:
   modelName: meta-llama/Llama-2-7b-hf
   criticality: Critical
   poolRef:
-    name: my-pool
+    name: vllm-llama2-7b
 
 ---
 apiVersion: inference.networking.x-k8s.io/v1alpha2
@@ -31,4 +31,4 @@ spec:
   modelName: Qwen/Qwen2.5-1.5B-Instruct
   criticality: Critical
   poolRef:
-    name: my-pool
+    name: vllm-llama2-7b
diff --git a/config/manifests/inferencepool.yaml b/config/manifests/inferencepool.yaml
index 640086393..8225bd7c7 100644
--- a/config/manifests/inferencepool.yaml
+++ b/config/manifests/inferencepool.yaml
@@ -75,6 +75,39 @@ spec:
           initialDelaySeconds: 5
           periodSeconds: 10
 ---
+apiVersion: gateway.envoyproxy.io/v1alpha1
+kind: EnvoyExtensionPolicy
+metadata:
+  name: ext-proc-policy
+  namespace: default
+spec:
+  extProc:
+    - backendRefs:
+      - group: ""
+        kind: Service
+        name: vllm-llama2-7b-epp
+        port: 9002
+      processingMode:
+        allowModeOverride: true
+        request:
+          body: Buffered
+        response:
+      # The timeouts are likely not needed here. We can experiment with removing/tuning them slowly.
+      # The connection limits are more important and will cause the opaque: ext_proc_gRPC_error_14 error in Envoy GW if not configured correctly. 
+      messageTimeout: 1000s
+      backendSettings:
+        circuitBreaker:
+          maxConnections: 40000
+          maxPendingRequests: 40000
+          maxParallelRequests: 40000
+        timeout:
+          tcp:
+            connectTimeout: 24h
+  targetRef:
+    group: gateway.networking.k8s.io
+    kind: HTTPRoute
+    name: llm-route
+---
 kind: ClusterRole
 apiVersion: rbac.authorization.k8s.io/v1
 metadata:
diff --git a/site-src/guides/index.md b/site-src/guides/index.md
index d6ff84594..d721e73ff 100644
--- a/site-src/guides/index.md
+++ b/site-src/guides/index.md
@@ -88,7 +88,6 @@ This quickstart guide is intended for engineers familiar with k8s and model serv
 ### Deploy Envoy Gateway Custom Policies
 
    ```bash
-   kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/extension_policy.yaml
    kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/patch_policy.yaml
    ```
    > **_NOTE:_** This is also per InferencePool, and will need to be configured to support the new pool should you wish to experiment further.
@@ -125,7 +124,7 @@ This quickstart guide is intended for engineers familiar with k8s and model serv
    kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/traffic_policy.yaml --ignore-not-found
    kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/extension_policy.yaml --ignore-not-found
    kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/patch_policy.yaml --ignore-not-found
-   kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/ext_proc.yaml --ignore-not-found
+   kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/inferencepool.yaml --ignore-not-found
    kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/gateway.yaml --ignore-not-found
    kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/enable_patch_policy.yaml --ignore-not-found
    kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/inferencemodel.yaml --ignore-not-found