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
  annotations:
    nvidia.com/enable-grove: "false" # temporarily disable grove because current k8s connector does not work with grove
spec:
  envs:
    - name: DYNAMO_SERVICE_CONFIG
      value: '{"Prometheus":{"global":{"scrape_interval":"5s"},"scrape_configs":[{"job_name":"prometheus","static_configs":[{"targets":["localhost:9090"]}]},{"job_name":"frontend","static_configs":[{"targets":["vllm-disagg-planner-frontend:8000"]}]}]}}'
    - name: DYNAMO_NAMESPACE
      value: "vllm-disagg-planner"
    - name: PROMETHEUS_PORT
      value: "8000"
  services:
    Frontend:
      dynamoNamespace: vllm-disagg-planner
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidian/nim-llm-dev/vllm-runtime:dep-301.6
          args:
            - "python3 -m dynamo.frontend --http-port 8000"
    Planner:
      dynamoNamespace: vllm-disagg-planner
      envFromSecret: hf-token-secret
      componentType: planner
      replicas: 1
      livenessProbe:
        httpGet:
          path: /metrics
          port: 9085
        periodSeconds: 60
        timeoutSeconds: 30
        failureThreshold: 10
      readinessProbe:
        httpGet:
          path: /metrics
          port: 9085
        initialDelaySeconds: 60
        periodSeconds: 60
        timeoutSeconds: 30
        failureThreshold: 10
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidian/nim-llm-dev/vllm-runtime:dep-301.6
          workingDir: /workspace/components/planner/src/dynamo/planner
          ports:
            - name: metrics
              containerPort: 9085
          command:
            - /bin/sh
            - -c
          args:
            - >-
              python3 -m planner_sla
              --environment=kubernetes
              --backend=vllm
              --adjustment-interval=60
              --profile-results-dir=/workspace/tests/planner/profiling_results/H200_TP1P_TP1D
              --prometheus-port=9085
              --ttft=0.1
              --itl=0.01
              --load-predictor=constant
    Prometheus: # NOTE: this is set on Prometheus to ensure a service is created for the Prometheus component. This is a workaround and should be managed differently.
      dynamoNamespace: vllm-disagg-planner
      componentType: prometheus
      replicas: 1
      envs:
        - name: PYTHONPATH
          value: "/workspace/components/planner/src"
      livenessProbe:
        httpGet:
          path: /
          port: 9090
        periodSeconds: 60
        timeoutSeconds: 30
        failureThreshold: 10
      readinessProbe:
        httpGet:
          path: /
          port: 9090
        initialDelaySeconds: 30
        periodSeconds: 60
        timeoutSeconds: 30
        failureThreshold: 10
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidian/nim-llm-dev/vllm-runtime:dep-301.6
          workingDir: /workspace/components/backends/vllm
          command:
            - /bin/sh
            - -c
          args:
            - "python3 -m dynamo.planner.prometheus"
    VllmDecodeWorker:
      dynamoNamespace: vllm-disagg-planner
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          startupProbe:
            httpGet:
              path: /health
              port: 9090
            periodSeconds: 30
            failureThreshold: 60
          image: nvcr.io/nvidian/nim-llm-dev/vllm-runtime:dep-301.6
          workingDir: /workspace/components/backends/vllm
          command:
            - /bin/sh
            - -c
          args:
            - "python3 -m dynamo.vllm --model nvidia/Llama-3.1-8B-Instruct-FP8 --migration-limit=3 --max-model-len=8192"
    VllmPrefillWorker:
      dynamoNamespace: vllm-disagg-planner
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          startupProbe:
            httpGet:
              path: /health
              port: 9090
            periodSeconds: 30
            failureThreshold: 60
          image: nvcr.io/nvidian/nim-llm-dev/vllm-runtime:dep-301.6
          workingDir: /workspace/components/backends/vllm
          command:
            - /bin/sh
            - -c
          args:
            - python3 -m dynamo.vllm --model nvidia/Llama-3.1-8B-Instruct-FP8 --is-prefill-worker --migration-limit=3 --max-model-len=8192