# 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 spec: services: Frontend: dynamoNamespace: vllm-disagg componentType: frontend replicas: 1 extraPodSpec: mainContainer: image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag VllmDecodeWorker: dynamoNamespace: vllm-disagg envFromSecret: hf-token-secret componentType: worker replicas: 1 resources: limits: gpu: "1" extraPodSpec: mainContainer: image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag workingDir: /workspace/components/backends/vllm command: - /bin/sh - -c args: - "python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B" VllmPrefillWorker: dynamoNamespace: vllm-disagg envFromSecret: hf-token-secret componentType: worker replicas: 1 resources: limits: gpu: "1" extraPodSpec: mainContainer: image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag workingDir: /workspace/components/backends/vllm command: - /bin/sh - -c args: - "python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --is-prefill-worker"