# 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: trtllm-disagg spec: services: Frontend: dynamoNamespace: trtllm-disagg componentType: frontend replicas: 1 extraPodSpec: mainContainer: image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17 TRTLLMPrefillWorker: dynamoNamespace: trtllm-disagg envFromSecret: hf-token-secret componentType: worker replicas: 1 resources: limits: gpu: "1" extraPodSpec: mainContainer: image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17 workingDir: /workspace/components/backends/trtllm command: - /bin/sh - -c args: - "python3 -m dynamo.trtllm --model-path Qwen/Qwen3-0.6B --served-model-name Qwen/Qwen3-0.6B --extra-engine-args engine_configs/prefill.yaml --disaggregation-mode prefill --disaggregation-strategy decode_first" TRTLLMDecodeWorker: dynamoNamespace: trtllm-disagg envFromSecret: hf-token-secret componentType: worker replicas: 1 resources: limits: gpu: "1" extraPodSpec: mainContainer: image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17 workingDir: /workspace/components/backends/trtllm command: - /bin/sh - -c args: - "python3 -m dynamo.trtllm --model-path Qwen/Qwen3-0.6B --served-model-name Qwen/Qwen3-0.6B --extra-engine-args engine_configs/decode.yaml --disaggregation-mode decode --disaggregation-strategy decode_first"