docs: hello world deploy example (#2102)

docs/examples/README.md

@@ -4,6 +4,9 @@
 
 Follow individual examples under components/backends/ to serve models locally.
 
+For example follow the [vLLM Backend Example](../../components/backends/vllm/README.md)
+
+For a basic GPU - unaware example see the [Hello World Example](../../examples/runtime/hello_world/README.md)
 
 ## Deploying Examples to Kubernetes
 
@@ -14,14 +17,9 @@ Before you can deploy your graphs, you need to deploy the Dynamo Runtime and Dyn
 If you are a **👤 Dynamo User** first follow the [Quickstart Guide](../guides/dynamo_deploy/quickstart.md) first.
 
 ### Instructions for Dynamo Contributor
-If you are a **🧑‍💻 Dynamo Contributor** first follow the instructions in [deploy/cloud/helm/README.md](../../deploy/cloud/helm/README.md) to create your Dynamo Cloud deployment.
-
-
-You would have to rebuild the dynamo platform images as the code evolves. For more details please look at the [Cloud Guide](../guides/dynamo_deploy/dynamo_cloud.md)
-
-```bash
-export DYNAMO_IMAGE=<your-registry>/<your-image-name>:<your-tag>
-```
+If you are a **🧑‍💻 Dynamo Contributor** you may have to rebuild the dynamo platform images as the code evolves.
+For more details read the [Cloud Guide](../guides/dynamo_deploy/dynamo_cloud.md)
+Read more on deploying Dynamo Cloud read [deploy/cloud/helm/README.md](../../deploy/cloud/helm/README.md).
 
 
 ### Deploying a particular example
@@ -42,12 +40,26 @@ kubectl apply -f components/backends/vllm/deploy/agg.yaml -n ${NAMESPACE}
 You can use `kubectl get dynamoGraphDeployment -n ${NAMESPACE}` to view your deployment.
 You can use `kubectl delete dynamoGraphDeployment <your-dep-name> -n ${NAMESPACE}` to delete the deployment.
 
+We provide a Custom Resource yaml file for many examples under the `deploy/` folder.
+Use [VLLM YAML](../../components/backends/vllm/deploy/agg.yaml) for an example.
+
 
 **Note 1** Example Image
 
-The examples use a prebuilt image from the `nvcr.io/nvidian/nim-llm-dev registry`.
+The examples use a prebuilt image from the `nvcr.io` registry.
 You can build your own image and update the image location in your CR file prior to applying.
-See [Building the Dynamo Base Image](../../README.md#building-the-dynamo-base-image)
+You could build your own image using
+
+```bash
+./container/build.sh --framework <your-inference-framework>
+```
+
+For example for the `sglang` run
+```bash
+./container/build.sh --framework sglang
+```
+
+Then you would need to overwrite the image in the examples.
 
 ```bash
 extraPodSpec:
@@ -72,4 +84,4 @@ kubectl port-forward svc/${SERVICE_NAME}-frontend 8080:8080 -n ${NAMESPACE}
 
 Consult the [Port Forward Documentation](https://kubernetes.io/docs/tasks/access-application-cluster/port-forward-access-application-cluster/)
 
-More on [LLM examples](llm_deployment.md)
+

examples/runtime/hello_world/README.md

@@ -101,3 +101,19 @@ Hello star!
 
 - **`worker`**: A dynamo worker that connects to the backend service and processes the streaming response
 
+## Deployment to Kubernetes
+
+Follow the [Quickstart Guide](../../../docs/guides/dynamo_deploy/quickstart.md) to install Dynamo Cloud.
+Then deploy to kubernetes using
+
+```bash
+export NAMESPACE=<your-namespace>
+cd dynamo
+kubectl apply -f examples/runtime/hello_world/deploy/hello_world.yaml -n ${NAMESPACE}
+```
+
+to delete your deployment:
+
+```bash
+kubectl delete dynamographdeployment hello-world -n ${NAMESPACE}
+```
\ No newline at end of file

examples/runtime/hello_world/deploy/hello_world.yaml

+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: nvidia.com/v1alpha1
+kind: DynamoGraphDeployment
+metadata:
+  name: hello-world
+spec:
+  services:
+    Frontend:
+      livenessProbe:
+        httpGet:
+          path: /health
+          port: 8000
+        initialDelaySeconds: 10
+        periodSeconds: 10
+        timeoutSeconds: 2
+        failureThreshold: 3
+      readinessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - 'echo ok'
+        initialDelaySeconds: 10
+        periodSeconds: 10
+        timeoutSeconds: 2
+        failureThreshold: 3
+      dynamoNamespace: hello-world
+      componentType: main
+      replicas: 1
+      resources:
+        requests:
+          cpu: "1"
+          memory: "2Gi"
+        limits:
+          cpu: "1"
+          memory: "2Gi"
+      extraPodSpec:
+        mainContainer:
+          image: gitlab-master.nvidia.com:5005/dl/ai-dynamo/dynamo/dynamo:helloworld
+          workingDir: /workspace/examples/runtime/hello_world/
+          command:
+            - /bin/sh
+            - -c
+          args:
+            - "python3 client.py"
+    HelloWorldWorker:
+      livenessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - "exit 0"
+        periodSeconds: 5
+        timeoutSeconds: 2
+        failureThreshold: 3
+      readinessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - 'grep "Serving endpoint" /tmp/hello_world.log'
+        initialDelaySeconds: 60
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
+      dynamoNamespace: hello-world
+      componentType: worker
+      replicas: 1
+      resources:
+        requests:
+          cpu: "1"
+          memory: "4Gi"
+        limits:
+          cpu: "1"
+          memory: "4Gi"
+      extraPodSpec:
+        mainContainer:
+          image: gitlab-master.nvidia.com:5005/dl/ai-dynamo/dynamo/dynamo:helloworld
+          workingDir: /workspace/examples/runtime/hello_world/
+          command:
+            - /bin/sh
+            - -c
+          args:
+            - python3 hello_world.py 2>&1 | tee /tmp/hello_world.log