Split the extension policy since it is envoy specific (kubernetes-sigs#524)

* split the extension policy since it is envoy specific

* merge extenstion and patch policy in one manifests

Author: ahg-g

config/manifests/gateway/patch_policy.yaml

@@ -85,4 +85,36 @@ spec:
     #     op: replace
     #     path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/response_header_mode"
     #     value: SEND
-
+---
+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

config/manifests/inferencepool.yaml

@@ -75,39 +75,6 @@ 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: