forked from ai-dynamo/dynamo
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathagg_router.yaml
More file actions
45 lines (44 loc) · 1.23 KB
/
Copy pathagg_router.yaml
File metadata and controls
45 lines (44 loc) · 1.23 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
# 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: vllm-agg-router
spec:
services:
Frontend:
componentType: frontend
replicas: 1
extraPodSpec:
mainContainer:
image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
envs:
- name: DYN_ROUTER_MODE
value: kv
VllmDecodeWorker:
envFromSecret: hf-token-secret
componentType: worker
replicas: 4
resources:
limits:
gpu: "1"
envs:
- name: DYN_LOG
value: "debug"
extraPodSpec:
volumes:
- name: local-model-cache
hostPath:
path: /YOUR/LOCAL/CACHE/FOLDER
type: DirectoryOrCreate
mainContainer:
image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
volumeMounts:
- name: local-model-cache
mountPath: /root/.cache
workingDir: /workspace/examples/backends/vllm
command:
- /bin/sh
- -c
args:
- python3 -m dynamo.vllm --model Qwen/Qwen2.5-1.5B-Instruct