disagg.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: vllm-disagg
spec:
  services:
    Frontend:
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: my-registry/vllm-runtime:my-tag
    VllmDecodeWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: decode
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          startupProbe:
            initialDelaySeconds: 180
          image: my-registry/vllm-runtime:my-tag
          workingDir: /workspace/examples/backends/vllm
          command:
            - /bin/sh
            - -c
          args:
          - |
            export LD_LIBRARY_PATH=/usr/local/nvidia/lib64:$LD_LIBRARY_PATH
            export PATH=$PATH:/usr/local/nvidia/bin:/usr/local/nvidia/lib64
            /sbin/ldconfig
            python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B
    VllmPrefillWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: prefill
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: my-registry/vllm-runtime:my-tag
          workingDir: /workspace/examples/backends/vllm
          command:
            - /bin/sh
            - -c
          args:
          - |
            export LD_LIBRARY_PATH=/usr/local/nvidia/lib64:$LD_LIBRARY_PATH
            export PATH=$PATH:/usr/local/nvidia/bin:/usr/local/nvidia/lib64
            /sbin/ldconfig
            python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --is-prefill-worker