feat: update DynamoGraphDeployments for vllm_v1

examples/vllm/README.md

@@ -116,6 +116,40 @@ bash launch/dep.sh
 > [!TIP]
 > Run a disaggregated example and try adding another prefill worker once the setup is running! The system will automatically discover and utilize the new worker.
 
+### Kubernetes Deployment
+
+For Kubernetes deployment, YAML manifests are provided in the `deploy/` directory. These define DynamoGraphDeployment resources for various configurations:
+
+- `agg.yaml` - Aggregated serving
+- `agg_router.yaml` - Aggregated serving with KV routing
+- `disagg.yaml` - Disaggregated serving
+- `disagg_router.yaml` - Disaggregated serving with KV routing
+
+#### Prerequisites
+
+- **Dynamo Cloud**: Follow the [Quickstart Guide](../../docs/guides/dynamo_deploy/quickstart.md) to deploy Dynamo Cloud first.
+
+- **Container Images**: The deployment files currently require access to `nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime`. If you don't have access, build and push your own image:
+  ```bash
+  ./container/build.sh --framework VLLM_V1
+  # Tag and push to your container registry
+  # Update the image references in the YAML files
+  ```
+
+- **Port Forwarding**: After deployment, forward the frontend service to access the API:
+  ```bash
+  kubectl port-forward deployment/vllm-v1-disagg-frontend-<pod-uuid-info> 8080:8000
+  ```
+
+#### Deploy to Kubernetes
+
+Example with disagg:
+
+```bash
+cd ~/dynamo/examples/vllm/deploy
+kubectl apply -f disagg.yaml
+```
+
 ### Testing the Deployment
 
 Send a test request to verify your deployment:

examples/vllm/deploy/agg.yaml

@@ -15,10 +15,28 @@
 apiVersion: nvidia.com/v1alpha1
 kind: DynamoGraphDeployment
 metadata:
-  name: agg
+  name: vllm-v1-agg
 spec:
   services:
     Frontend:
+      livenessProbe:
+        httpGet:
+          path: /health
+          port: 8000
+        initialDelaySeconds: 60
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
+      readinessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - 'curl -s http://localhost:8000/health | jq -e ".status == \"healthy\""'
+        initialDelaySeconds: 60
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
       dynamoNamespace: vllm-v1-agg
       componentType: main
       replicas: 1
@@ -31,50 +49,38 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
-          workingDir: /workspace/examples/vllm_v1
+          image: nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
+          workingDir: /workspace/examples/vllm
           args:
             - dynamo
-            - serve
-            - graphs.agg:Frontend
-            - --system-app-port
-            - "5000"
-            - --enable-system-app
-            - --use-default-health-checks
-            - --service-name
-            - Frontend
-            - -f
-            - ./configs/agg.yaml
-    SimpleLoadBalancer:
-      envFromSecret: hf-token-secret
-      dynamoNamespace: vllm-v1-agg
-      replicas: 1
-      resources:
-        requests:
-          cpu: "1"
-          memory: "20Gi"
-        limits:
-          cpu: "1"
-          memory: "20Gi"
-      extraPodSpec:
-        mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
-          workingDir: /workspace/examples/vllm_v1
-          args:
-            - dynamo
-            - serve
-            - graphs.agg:SimpleLoadBalancer
-            - --system-app-port
-            - "5000"
-            - --enable-system-app
-            - --use-default-health-checks
-            - --service-name
-            - SimpleLoadBalancer
-            - -f
-            - ./configs/agg.yaml
+            - run
+            - in=http
+            - out=dyn
+            - --http-port
+            - "8000"
     VllmDecodeWorker:
       envFromSecret: hf-token-secret
+      livenessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - "exit 0"
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
+      readinessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - 'grep "VllmWorker.*has been initialized" /tmp/vllm.log'
+        initialDelaySeconds: 60
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
       dynamoNamespace: vllm-v1-agg
+      componentType: worker
       replicas: 1
       resources:
         requests:
@@ -87,17 +93,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
-          workingDir: /workspace/examples/vllm_v1
+          image: nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
+          workingDir: /workspace/examples/vllm
           args:
-            - dynamo
-            - serve
-            - graphs.agg:VllmDecodeWorker
-            - --system-app-port
-            - "5000"
-            - --enable-system-app
-            - --use-default-health-checks
-            - --service-name
-            - VllmDecodeWorker
-            - -f
-            - ./configs/agg.yaml
+            - "python3 components/main.py --model Qwen/Qwen3-0.6B --enforce-eager 2>&1 | tee /tmp/vllm.log"

examples/vllm/deploy/agg_router.yaml

@@ -0,0 +1,99 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+apiVersion: nvidia.com/v1alpha1
+kind: DynamoGraphDeployment
+metadata:
+  name: vllm-v1-agg
+spec:
+  services:
+    Frontend:
+      livenessProbe:
+        httpGet:
+          path: /health
+          port: 8000
+        initialDelaySeconds: 60
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
+      readinessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - 'curl -s http://localhost:8000/health | jq -e ".status == \"healthy\""'
+        initialDelaySeconds: 60
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
+      dynamoNamespace: vllm-v1-agg
+      componentType: main
+      replicas: 1
+      resources:
+        requests:
+          cpu: "1"
+          memory: "2Gi"
+        limits:
+          cpu: "1"
+          memory: "2Gi"
+      extraPodSpec:
+        mainContainer:
+          image: nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
+          workingDir: /workspace/examples/vllm
+          args:
+            - dynamo
+            - run
+            - in=http
+            - out=dyn
+            - --http-port
+            - "8000"
+    VllmDecodeWorker:
+      envFromSecret: hf-token-secret
+      livenessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - "exit 0"
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
+      readinessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - 'grep "VllmWorker.*has been initialized" /tmp/vllm.log'
+        initialDelaySeconds: 60
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
+      dynamoNamespace: vllm-v1-agg
+      componentType: worker
+      replicas: 2
+      resources:
+        requests:
+          cpu: "10"
+          memory: "20Gi"
+          gpu: "1"
+        limits:
+          cpu: "10"
+          memory: "20Gi"
+          gpu: "1"
+      extraPodSpec:
+        mainContainer:
+          image: nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
+          workingDir: /workspace/examples/vllm
+          args:
+            - "python3 components/main.py --model Qwen/Qwen3-0.6B --enforce-eager 2>&1 | tee /tmp/vllm.log"