disagg_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-v1-disagg-router
spec:
  services:
    Frontend:
      dynamoNamespace: vllm-v1-disagg-router
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidian/nim-llm-dev/vllm-runtime:dep-233.17
          workingDir: /workspace/components/backends/vllm
          command:
            - /bin/sh
            - -c
          args:
            - "python3 -m dynamo.frontend --http-port 8000 --router-mode kv"
    VllmDecodeWorker:
      dynamoNamespace: vllm-v1-disagg-router
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 2
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidian/nim-llm-dev/vllm-runtime:dep-233.17
          workingDir: /workspace/components/backends/vllm
          command:
            - /bin/sh
            - -c
          args:
            - python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B
    VllmPrefillWorker:
      dynamoNamespace: vllm-v1-disagg-router
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidian/nim-llm-dev/vllm-runtime:dep-233.17
          workingDir: /workspace/components/backends/vllm
          command:
            - /bin/sh
            - -c
          args:
            - python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --is-prefill-worker