agg_router.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: vllm-agg-router
spec:
  services:
    Frontend:
      dynamoNamespace: vllm-agg-router
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
      envs:
        - name: DYN_ROUTER_MODE
          value: kv
    VllmDecodeWorker:
      envFromSecret: hf-token-secret
      dynamoNamespace: vllm-agg-router
      componentType: worker
      replicas: 4
      resources:
        limits:
          gpu: "1"
      envs:
        - name: DYN_LOG
          value: "debug"
      extraPodSpec:
        volumes:
        - name: local-model-cache
          hostPath:
            path: /YOUR/LOCAL/CACHE/FOLDER
            type: DirectoryOrCreate
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          volumeMounts:
          - name: local-model-cache
            mountPath: /root/.cache
          workingDir: /workspace/examples/backends/vllm
          command:
            - /bin/sh
            - -c
          args:
            - python3 -m dynamo.vllm --model Qwen/Qwen2.5-1.5B-Instruct