# 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: agg-llava spec: backendFramework: vllm services: Frontend: componentType: frontend replicas: 1 extraPodSpec: mainContainer: image: my-registry/vllm-runtime:my-tag EncodeWorker: envFromSecret: hf-token-secret componentType: worker replicas: 1 resources: limits: gpu: "1" extraPodSpec: mainContainer: image: my-registry/vllm-runtime:my-tag workingDir: /workspace/examples/multimodal command: - /bin/sh - -c args: - python3 components/encode_worker.py --model llava-hf/llava-1.5-7b-hf VLMWorker: envFromSecret: hf-token-secret componentType: worker replicas: 1 resources: limits: gpu: "1" extraPodSpec: mainContainer: image: my-registry/vllm-runtime:my-tag workingDir: /workspace/examples/multimodal command: - /bin/sh - -c args: - python3 components/worker.py --model llava-hf/llava-1.5-7b-hf --worker-type prefill Processor: envFromSecret: hf-token-secret componentType: worker replicas: 1 resources: limits: gpu: "1" extraPodSpec: mainContainer: image: my-registry/vllm-runtime:my-tag workingDir: /workspace/examples/multimodal command: - /bin/sh - -c args: - 'python3 components/processor.py --model llava-hf/llava-1.5-7b-hf --prompt-template "USER: \n ASSISTANT:"'