# 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: trtllm-agg spec: services: Frontend: componentType: frontend replicas: 1 extraPodSpec: mainContainer: image: my-registry/tensorrtllm-runtime:my-tag TRTLLMWorker: envFromSecret: hf-token-secret componentType: worker replicas: 1 resources: limits: gpu: "1" requests: custom: # Increase this value for larger models ephemeral-storage: "2Gi" extraPodSpec: mainContainer: image: my-registry/tensorrtllm-runtime:my-tag workingDir: /workspace/ command: - python3 - -m - dynamo.trtllm args: - --model-path - Qwen/Qwen3-0.6B - --served-model-name - Qwen/Qwen3-0.6B - --extra-engine-args - ./examples/backends/trtllm/engine_configs/qwen3/agg.yaml