fix: Recipe namespace fix (#4445)

Signed-off-by: Anna Tchernych <atchernych@nvidia.com>

recipes/README.md

@@ -147,16 +147,6 @@ kubectl logs -f job/<benchmark-job-name> -n ${NAMESPACE}
 kubectl logs job/<benchmark-job-name> -n ${NAMESPACE} | tail -50
 ```
 
-** Inference Gateway (GAIE) Integration (Optional)**
-
-For Llama-3-70B with vLLM (Aggregated), an example of integration with the Inference Gateway is provided.
-
-Follow to Follow [Deploy Inference Gateway Section 2](../deploy/inference-gateway/README.md#2-deploy-inference-gateway) to install GAIE. Then apply manifests.
-
-```bash
-export DEPLOY_PATH=llama-3-70b/vllm/agg/
-#DEPLOY_PATH=<model>/<framework>/<mode>/
-kubectl apply -R -f "$DEPLOY_PATH/gaie/k8s-manifests" -n "$NAMESPACE"
 
 ## Example Deployments
 
@@ -180,6 +170,19 @@ kubectl apply -f llama-3-70b/vllm/agg/deploy.yaml -n ${NAMESPACE}
 kubectl port-forward svc/llama3-70b-agg-frontend 8000:8000 -n ${NAMESPACE}
 ```
 
+### Inference Gateway (GAIE) Integration (Optional)**
+
+For Llama-3-70B with vLLM (Aggregated), an example of integration with the Inference Gateway is provided.
+
+Follow to Follow [Deploy Inference Gateway Section 2](../deploy/inference-gateway/README.md#2-deploy-inference-gateway) to install GAIE. Then apply manifests.
+Update the containers.epp.image in the deployment file, i.e. llama-3-70b/vllm/agg/gaie/k8s-manifests/epp/deployment.yaml
+
+```bash
+export DEPLOY_PATH=llama-3-70b/vllm/agg/
+#DEPLOY_PATH=<model>/<framework>/<mode>/
+kubectl apply -R -f "$DEPLOY_PATH/gaie/k8s-manifests" -n "$NAMESPACE"
+
+
 ### DeepSeek-R1 on GB200 (Multi-node)
 
 See [deepseek-r1/trtllm/disagg/wide_ep/gb200/deploy.yaml](deepseek-r1/trtllm/disagg/wide_ep/gb200/deploy.yaml) for the complete multi-node WideEP configuration.

recipes/llama-3-70b/vllm/agg/gaie/k8s-manifests/epp/configmap.yaml

@@ -20,7 +20,6 @@ metadata:
   name: epp-config
   labels:
     app.kubernetes.io/name: dynamo-gaie
-    app.kubernetes.io/instance: llama3-70b-agg
 data:
   epp-config-dynamo.yaml: |
     apiVersion: inference.networking.x-k8s.io/v1alpha1

recipes/llama-3-70b/vllm/agg/gaie/k8s-manifests/epp/deployment.yaml

@@ -38,7 +38,7 @@ spec:
 
       containers:
         - name: epp
-          image: nvcr.io/nvstaging/ai-dynamo/epp-inference-extension-dynamo:v0.6.0-1
+          image: nvcr.io/nvstaging/ai-dynamo/dynamo-frontend:0.7.0rc2-amd64
           imagePullPolicy: IfNotPresent
           resources:
             requests:
@@ -73,8 +73,8 @@ spec:
               value: "dynamo-platform-etcd.$(PLATFORM_NAMESPACE):2379" #  update dynamo-platform to appropriate namespace
             - name: NATS_SERVER
               value: "nats://dynamo-platform-nats.$(PLATFORM_NAMESPACE):4222" #  update dynamo-platform to appropriate namespace
-            - name: DYN_NAMESPACE
-              value: "llama3-70b-agg"
+            - name: DYNAMO_NAMESPACE
+              value: "$(POD_NAMESPACE)-llama3-70b-agg"
             - name: DYNAMO_KV_BLOCK_SIZE
               value: "128" # UPDATE to match the --block-size in your deploy.yaml engine command
             - name: USE_STREAMING

recipes/llama-3-70b/vllm/agg/gaie/k8s-manifests/epp/service.yaml

@@ -20,11 +20,10 @@ metadata:
   name: llama3-70b-agg-epp
 spec:
   selector:
-    app: llama3-70b-agg
+    app: llama3-70b-agg-epp
   ports:
     - protocol: TCP
       port: 9002
       targetPort: 9002
       appProtocol: http2
   type: ClusterIP
-

recipes/llama-3-70b/vllm/agg/gaie/k8s-manifests/model/inference-model.yaml

@@ -25,4 +25,3 @@ spec:
     group: inference.networking.x-k8s.io
     kind: InferencePool
     name: llama3-70b-agg-pool
-

recipes/llama-3-70b/vllm/agg/gaie/k8s-manifests/model/inference-pool.yaml

@@ -22,7 +22,6 @@ spec:
   targetPortNumber: 8000
   selector:
     nvidia.com/dynamo-component: Frontend
-    nvidia.com/dynamo-namespace: llama3-70b-agg # # This is the Dynamo namespace where the model is deployed
   extensionRef:
     failureMode: FailOpen
     group: ""