# 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 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", "throughput_adjustment_interval": 60, "profile_results_dir": "/workspace/tests/planner/profiling_results/H200_TP1P_TP1D", "no_correction": true}' 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 - --disaggregation-mode - decode 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