disagg_planner.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-disagg-planner
spec:
  pvcs:
    - name: dynamo-pvc
      create: false # Must be pre-created before deployment and SLA profiler must have been run
  envs:
    - name: DYNAMO_NAMESPACE
      value: "vllm-disagg-planner"
  services:
    Frontend:
      dynamoNamespace: vllm-disagg-planner
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
    Planner:
      dynamoNamespace: vllm-disagg-planner
      envFromSecret: hf-token-secret
      componentType: planner
      replicas: 1
      livenessProbe:
        exec:
          command:
            - /bin/sh
            - -c
            - "exit 0"
        periodSeconds: 60
        timeoutSeconds: 30
        failureThreshold: 10
      readinessProbe:
        exec:
          command:
            - /bin/sh
            - -c
            - "exit 0"
        initialDelaySeconds: 60
        periodSeconds: 60
        timeoutSeconds: 30
        failureThreshold: 10
      volumeMounts:
        - name: dynamo-pvc
          mountPoint: /data
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          workingDir: /workspace/components/planner/src/dynamo/planner
          command:
          - python3
          - -m
          - planner_sla
          args:
            - --environment=kubernetes
            - --backend=vllm
            - --adjustment-interval=60
            - --profile-results-dir=/data/profiling_results
    VllmDecodeWorker:
      dynamoNamespace: vllm-disagg-planner
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: decode
      replicas: 2
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          startupProbe:
            httpGet:
              path: /health
              port: 9090
            periodSeconds: 10
            failureThreshold: 60
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          workingDir: /workspace/components/backends/vllm
          command:
            - python3
          args:
            - -m
            - dynamo.vllm
            - --model
            - Qwen/Qwen3-0.6B
    VllmPrefillWorker:
      dynamoNamespace: vllm-disagg-planner
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: prefill
      replicas: 2
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          startupProbe:
            httpGet:
              path: /health
              port: 9090
            periodSeconds: 10
            failureThreshold: 60
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          workingDir: /workspace/components/backends/vllm
          command:
            - python3
          args:
            - -m
            - dynamo.vllm
            - --model
            - Qwen/Qwen3-0.6B
            - --is-prefill-worker