agg_qwen.yaml

# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0

apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: agg-qwen
spec:
  backendFramework: vllm
  services:
    Frontend:
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: my-registry/vllm-runtime:my-tag
    EncodeWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: my-registry/vllm-runtime:my-tag
          workingDir: /workspace/examples/multimodal
          command:
            - /bin/sh
            - -c
          args:
            - python3 components/encode_worker.py --model Qwen/Qwen2.5-VL-7B-Instruct
    VLMWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: my-registry/vllm-runtime:my-tag
          workingDir: /workspace/examples/multimodal
          command:
            - /bin/sh
            - -c
          args:
            - python3 components/worker.py --model Qwen/Qwen2.5-VL-7B-Instruct --worker-type prefill
    Processor:
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: my-registry/vllm-runtime:my-tag
          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"'