# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Minimal GlobalPlanner GPU budget example: 2 independent model DGDs sharing a
# GPU cap enforced by a central GlobalPlanner.
#
# Each model DGD is self-contained (Frontend + Workers + Planner) and serves a
# different model. The GlobalPlanner in the ctrl DGD rejects any scale request
# that would push the total GPU count across its managed DGDs above MAX_TOTAL_GPUS.
#
# The budget applies only to DGDs managed by this GlobalPlanner (see
# --managed-namespaces), not to every DGD in the cluster. In this example the
# ctrl DGD runs in implicit mode (no --managed-namespaces), so all DGDs in the
# same K8s namespace count toward the budget. To limit the budget to specific
# DGDs, pass --managed-namespaces with their Dynamo namespaces.
#
# Architecture:
#   DGD gp-ctrl:    GlobalPlanner (--max-total-gpus)
#   DGD model-a:    Frontend + VllmPrefillWorker + VllmDecodeWorker + Planner  (MODEL_A)
#   DGD model-b:    Frontend + VllmPrefillWorker + VllmDecodeWorker + Planner  (MODEL_B)
#
# Prerequisites:
#   - Cluster Prometheus deployed and scraping pods via PodMonitor
#   - HuggingFace token secret: kubectl create secret generic hf-token-secret \
#       --from-literal=HF_TOKEN=<your-token> -n ${K8S_NAMESPACE}
#
# Usage:
#   export K8S_NAMESPACE=... DYNAMO_IMAGE=... DYNAMO_VLLM_IMAGE=... STORAGE_CLASS_NAME=...
#   export MODEL_A=meta-llama/Llama-3.1-8B-Instruct MODEL_B=Qwen/Qwen3-8B MAX_TOTAL_GPUS=8
#   envsubst < global-planner-gpu-budget.yaml | kubectl apply  -n ${K8S_NAMESPACE} -f -
#   envsubst < global-planner-gpu-budget.yaml | kubectl delete -n ${K8S_NAMESPACE} -f -
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: ${K8S_NAMESPACE}-planner
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: dynamo-platform-dynamo-operator-planner
subjects:
  - kind: ServiceAccount
    name: default
    namespace: ${K8S_NAMESPACE}
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: hf-model-cache
spec:
  accessModes:
    - ReadWriteMany
  storageClassName: ${STORAGE_CLASS_NAME}
  resources:
    requests:
      storage: 50Gi
---
# ── Control plane: GlobalPlanner only ────────────────────────────────────────
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: gp-ctrl
spec:
  services:
    GlobalPlanner:
      componentType: default
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: ${DYNAMO_IMAGE}
          command:
            - python3
            - -m
            - dynamo.global_planner
          args:
            - --max-total-gpus
            - "${MAX_TOTAL_GPUS}"
---
# ── Model A: self-contained disagg serving DGD ──────────────────────────────
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: model-a
spec:
  services:
    Frontend:
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: ${DYNAMO_IMAGE}
          workingDir: /workspace
          command:
            - python3
            - -m
            - dynamo.frontend
          args:
            - --model-name
            - ${MODEL_A}

    VllmPrefillWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: prefill
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        volumes:
          - name: hf-model-cache
            persistentVolumeClaim:
              claimName: hf-model-cache
        mainContainer:
          image: ${DYNAMO_VLLM_IMAGE}
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
            - -m
            - dynamo.vllm
          args:
            - --model
            - ${MODEL_A}
            - --tensor-parallel-size
            - "1"
            - --is-prefill-worker
          volumeMounts:
            - name: hf-model-cache
              mountPath: /home/dynamo/.cache/huggingface/hub

    VllmDecodeWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: decode
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        volumes:
          - name: hf-model-cache
            persistentVolumeClaim:
              claimName: hf-model-cache
        mainContainer:
          image: ${DYNAMO_VLLM_IMAGE}
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
            - -m
            - dynamo.vllm
          args:
            - --model
            - ${MODEL_A}
            - --tensor-parallel-size
            - "1"
          volumeMounts:
            - name: hf-model-cache
              mountPath: /home/dynamo/.cache/huggingface/hub

    Planner:
      componentType: planner
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: ${DYNAMO_IMAGE}
          command:
            - python3
            - -m
            - dynamo.planner
          args:
            - --config
            - '{"environment":"global-planner","global_planner_namespace":"${K8S_NAMESPACE}-gp-ctrl","backend":"vllm","mode":"disagg","enable_load_scaling":false,"enable_throughput_scaling":true,"throughput_metrics_source":"router","ttft":2000,"itl":200,"max_gpu_budget":-1,"prefill_engine_num_gpu":1,"decode_engine_num_gpu":1,"model_name":"${MODEL_A}","profile_results_dir":"/workspace/tests/planner/profiling_results/H200_TP1P_TP1D"}'
---
# ── Model B: self-contained disagg serving DGD ──────────────────────────────
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: model-b
spec:
  services:
    Frontend:
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: ${DYNAMO_IMAGE}
          workingDir: /workspace
          command:
            - python3
            - -m
            - dynamo.frontend
          args:
            - --model-name
            - ${MODEL_B}

    VllmPrefillWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: prefill
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        volumes:
          - name: hf-model-cache
            persistentVolumeClaim:
              claimName: hf-model-cache
        mainContainer:
          image: ${DYNAMO_VLLM_IMAGE}
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
            - -m
            - dynamo.vllm
          args:
            - --model
            - ${MODEL_B}
            - --tensor-parallel-size
            - "1"
            - --is-prefill-worker
          volumeMounts:
            - name: hf-model-cache
              mountPath: /home/dynamo/.cache/huggingface/hub

    VllmDecodeWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: decode
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        volumes:
          - name: hf-model-cache
            persistentVolumeClaim:
              claimName: hf-model-cache
        mainContainer:
          image: ${DYNAMO_VLLM_IMAGE}
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
            - -m
            - dynamo.vllm
          args:
            - --model
            - ${MODEL_B}
            - --tensor-parallel-size
            - "1"
          volumeMounts:
            - name: hf-model-cache
              mountPath: /home/dynamo/.cache/huggingface/hub

    Planner:
      componentType: planner
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: ${DYNAMO_IMAGE}
          command:
            - python3
            - -m
            - dynamo.planner
          args:
            - --config
            - '{"environment":"global-planner","global_planner_namespace":"${K8S_NAMESPACE}-gp-ctrl","backend":"vllm","mode":"disagg","enable_load_scaling":false,"enable_throughput_scaling":true,"throughput_metrics_source":"router","ttft":2000,"itl":200,"max_gpu_budget":-1,"prefill_engine_num_gpu":1,"decode_engine_num_gpu":1,"model_name":"${MODEL_B}","profile_results_dir":"/workspace/tests/planner/profiling_results/H200_TP1P_TP1D"}'