# 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: sglang-agg spec: services: Frontend: componentType: frontend replicas: 1 extraPodSpec: mainContainer: image: my-registry/sglang-runtime:my-tag decode: 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/sglang-runtime:my-tag workingDir: /workspace/examples/backends/sglang command: - python3 - -m - dynamo.sglang args: - --model-path - Qwen/Qwen3-0.6B - --served-model-name - Qwen/Qwen3-0.6B - --page-size - "16" - --tp - "1" - --trust-remote-code - --skip-tokenizer-init