feat: example routing between different models using inference gateway

deploy/inference-gateway/example/README.md

@@ -138,8 +138,10 @@ export GATEWAY_URL=<Gateway-URL>
 
 To test the gateway in minikube, use the following command:
 ```bash
-minikube tunnel &
+# start minikube tunnel
+minikube tunnel
 
+# in a separate terminal
 GATEWAY_URL=$(kubectl get svc inference-gateway -o yaml -o jsonpath='{.spec.clusterIP}')
 echo $GATEWAY_URL
 ```

deploy/inference-gateway/example/two_models/README.md

@@ -0,0 +1,68 @@
+Get Gatewaty URL
+```bash
+GATEWAY_URL=$(kubectl get svc inference-gateway -o yaml -o jsonpath='{.spec.clusterIP}')
+echo $GATEWAY_URL
+```
+
+Get models
+```bash
+curl $GATEWAY_URL/v1/models | jq .
+
+# Sample response
+{
+  "object": "list",
+  "data": [
+    {
+      "id": "google/gemma-3-1b-it",
+      "object": "object",
+      "created": 1752695871,
+      "owned_by": "nvidia"
+    },
+    {
+      "id": "Qwen/Qwen3-0.6B",
+      "object": "object",
+      "created": 1752695871,
+      "owned_by": "nvidia"
+    }
+  ]
+}
+```
+
+
+Send inference request to Qwen model:
+
+```bash
+curl $GATEWAY_URL/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "Qwen/Qwen3-0.6B",
+    "messages": [
+    {
+        "role": "user",
+        "content": "In the heart of Eldoria, an ancient land of boundless magic and mysterious creatures, lies the long-forgotten city of Aeloria. Once a beacon of knowledge and power, Aeloria was buried beneath the shifting sands of time, lost to the world for centuries. You are an intrepid explorer, known for your unparalleled curiosity and courage, who has stumbled upon an ancient map hinting at ests that Aeloria holds a secret so profound that it has the potential to reshape the very fabric of reality. Your journey will take you through treacherous deserts, enchanted forests, and across perilous mountain ranges. Your Task: Character Background: Develop a detailed background for your character. Describe their motivations for seeking out Aeloria, their skills and weaknesses, and any personal connections to the ancient city or its legends. Are they driven by a quest for knowledge, a search for lost familt clue is hidden."
+    }
+    ],
+    "stream":false,
+    "max_tokens": 30
+  }'
+```
+
+
+Send inference request to Gemma model:
+
+
+```bash
+curl $GATEWAY_URL/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "google/gemma-3-1b-it",
+    "messages": [
+    {
+        "role": "user",
+        "content": "In the heart of Eldoria, an ancient land of boundless magic and mysterious creatures, lies the long-forgotten city of Aeloria. Once a beacon of knowledge and power, Aeloria was buried beneath the shifting sands of time, lost to the world for centuries. You are an intrepid explorer, known for your unparalleled curiosity and courage, who has stumbled upon an ancient map hinting at ests that Aeloria holds a secret so profound that it has the potential to reshape the very fabric of reality. Your journey will take you through treacherous deserts, enchanted forests, and across perilous mountain ranges. Your Task: Character Background: Develop a detailed background for your character. Describe their motivations for seeking out Aeloria, their skills and weaknesses, and any personal connections to the ancient city or its legends. Are they driven by a quest for knowledge, a search for lost familt clue is hidden."
+    }
+    ],
+    "stream":false,
+    "max_tokens": 30
+  }'
+```

deploy/inference-gateway/example/resources/inference-model.yaml → deploy/inference-gateway/example/two_models/inference-model-gemma.yaml

@@ -15,11 +15,11 @@
 apiVersion: inference.networking.x-k8s.io/v1alpha2
 kind: InferenceModel
 metadata:
-  name: deep-seek-model
+  name: gemma3
   namespace: default
 spec:
   criticality: Critical
-  modelName: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+  modelName: google/gemma-3-1b-it
   poolRef:
     group: inference.networking.x-k8s.io
     kind: InferencePool

deploy/inference-gateway/example/two_models/inference-model-qwen.yaml

@@ -0,0 +1,26 @@
+# 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: inference.networking.x-k8s.io/v1alpha2
+kind: InferenceModel
+metadata:
+  name: qwen3
+  namespace: default
+spec:
+  criticality: Critical
+  modelName: Qwen/Qwen3-0.6B
+  poolRef:
+    group: inference.networking.x-k8s.io
+    kind: InferencePool
+    name: dynamo-deepseek

deploy/inference-gateway/example/two_models/two_models.yaml

@@ -0,0 +1,140 @@
+# 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
+            - "exit 0"
+        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: gitlab-master.nvidia.com:5005/aire/microservices/compoundai/dynamo:1c03404f2624186523529b8d4ca04731b60aa8b9-31776852-vllm_v1-amd64
+          workingDir: /workspace/examples/vllm
+          args:
+            - dynamo
+            - run
+            - in=http
+            - out=dyn
+            - --http-port
+            - "8000"
+            - --router-mode
+            - kv
+    GemmaDecodeWorker:
+      envFromSecret: hf-token-secret
+      livenessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - "exit 0"
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
+      readinessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - "exit 0"
+        initialDelaySeconds: 60
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
+      dynamoNamespace: vllm-v1-agg
+      componentType: worker
+      replicas: 1
+      resources:
+        requests:
+          cpu: "10"
+          memory: "20Gi"
+          gpu: "1"
+        limits:
+          cpu: "10"
+          memory: "20Gi"
+          gpu: "1"
+      extraPodSpec:
+        mainContainer:
+          image: gitlab-master.nvidia.com:5005/aire/microservices/compoundai/dynamo:1c03404f2624186523529b8d4ca04731b60aa8b9-31776852-vllm_v1-amd64
+          workingDir: /workspace/examples/vllm
+          args:
+            - "python3 components/main.py --model google/gemma-3-1b-it --enforce-eager --endpoint dyn://dynamo.gemma.generate 2>&1 | tee /tmp/vllm.log"
+    QwenDecodeWorker:
+      envFromSecret: hf-token-secret
+      livenessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - "exit 0"
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
+      readinessProbe:
+        exec:
+          command:
+            - /bin/sh
+            - -c
+            - "exit 0"
+        initialDelaySeconds: 60
+        periodSeconds: 60
+        timeoutSeconds: 30
+        failureThreshold: 10
+      dynamoNamespace: vllm-v1-agg
+      componentType: worker
+      replicas: 1
+      resources:
+        requests:
+          cpu: "10"
+          memory: "20Gi"
+          gpu: "1"
+        limits:
+          cpu: "10"
+          memory: "20Gi"
+          gpu: "1"
+      extraPodSpec:
+        mainContainer:
+          image: gitlab-master.nvidia.com:5005/aire/microservices/compoundai/dynamo:1c03404f2624186523529b8d4ca04731b60aa8b9-31776852-vllm_v1-amd64
+          workingDir: /workspace/examples/vllm
+          args:
+            - "python3 components/main.py --model Qwen/Qwen3-0.6B --enforce-eager --endpoint dyn://dynamo.qwen.generate 2>&1 | tee /tmp/vllm.log"