Unverified Commit 28f089d8 authored by dagil-nvidia's avatar dagil-nvidia Committed by GitHub
Browse files

fix: remove outdated deploy/discovery example (#7000)


Signed-off-by: default avatarDan Gil <dagil@nvidia.com>
parent d8828920
<!--
SPDX-FileCopyrightText: Copyright (c) 2024-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: Apache-2.0
-->
# Dynamo Service Discovery
For documentation on Dynamo's service discovery system, see the [Service Discovery Guide](../../docs/kubernetes/service-discovery.md).
# 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: dynamo
annotations:
nvidia.com/dynamo-discovery-backend: kubernetes
spec:
envs:
- name: DYN_LOG
value: "debug"
services:
Frontend:
componentType: frontend
replicas: 1
extraPodSpec:
mainContainer:
image: ${IMAGE}
VllmDecodeWorker:
componentType: decode
replicas: 1
resources:
limits:
gpu: "1"
extraPodSpec:
terminationGracePeriodSeconds: 120
mainContainer:
image: ${IMAGE}
workingDir: /workspace/components/backends/vllm
command:
- python3
- -m
- dynamo.vllm
args:
- --model
- Qwen/Qwen3-0.6B
VllmPrefillWorker:
componentType: prefill
replicas: 1
resources:
limits:
gpu: "1"
extraPodSpec:
terminationGracePeriodSeconds: 120
mainContainer:
image: ${IMAGE}
workingDir: /workspace/components/backends/vllm
command:
- python3
- -m
- dynamo.vllm
args:
- --model
- Qwen/Qwen3-0.6B
- --disaggregation-mode
- prefill
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment