disagg_planner_load.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-planner
spec:
  services:
    Frontend:
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
          args:
            - -m
            - dynamo.frontend
            - --router-mode
            - kv
    Planner:
      componentType: planner
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          command:
          - python3
          - -m
          - dynamo.planner
          args:
            - --config
            - '{"environment": "kubernetes", "backend": "vllm", "enable_load_scaling": true, "enable_throughput_scaling": false, "pre_deployment_sweeping_mode": "none", "load_adjustment_interval": 5, "load_min_observations": 5}'
    VllmDecodeWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: decode
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
          args:
            - -m
            - dynamo.vllm
            - --model
            - nvidia/Llama-3.1-8B-Instruct-FP8
    VllmPrefillWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: prefill
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
          args:
            - -m
            - dynamo.vllm
            - --model
            - nvidia/Llama-3.1-8B-Instruct-FP8
            - --disaggregation-mode
            - prefill