shared_frontend.yaml

# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: dynamo-model-cache
spec:
  accessModes:
    - ReadWriteOnce
  resources:
    requests:
      storage: 100Gi
---
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: frontend
spec:
  services:
    Frontend:
      componentType: frontend
      globalDynamoNamespace: true
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
---
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: vllm-agg
spec:
  pvcs:
  - name: dynamo-model-cache
    create: false
  services:
    VllmDecodeWorker:
      volumeMounts:
      - name: dynamo-model-cache
        mountPoint: /root/.cache/huggingface
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
          workingDir: /workspace/examples/backends/vllm
          command:
            - /bin/sh
            - -c
          args:
            - python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B
---
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: agg-qwen
spec:
  backendFramework: vllm
  services:
    EncodeWorker:
      volumeMounts:
      - name: dynamo-model-cache
        mountPoint: /root/.cache/huggingface
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
          workingDir: /workspace/examples/multimodal
          command:
            - /bin/sh
            - -c
          args:
            - python3 components/encode_worker.py --model Qwen/Qwen2.5-VL-7B-Instruct
    VLMWorker:
      volumeMounts:
      - name: dynamo-model-cache
        mountPoint: /root/.cache/huggingface
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
          workingDir: /workspace/examples/multimodal
          command:
            - /bin/sh
            - -c
          args:
            - python3 components/worker.py --model Qwen/Qwen2.5-VL-7B-Instruct --worker-type prefill
    Processor:
      volumeMounts:
      - name: dynamo-model-cache
        mountPoint: /root/.cache/huggingface
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
          workingDir: /workspace/examples/multimodal
          command:
            - /bin/sh
            - -c
          args:
            - 'python3 components/processor.py --model Qwen/Qwen2.5-VL-7B-Instruct --prompt-template "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|><prompt><|im_end|>\n<|im_start|>assistant\n"'