Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
shared_frontend.yaml 3.4 KB
Newer Older
Maksim Khadkevich's avatar
docs: added example for a frontend shared across multiple models (#3008)  
Maksim Khadkevich committed
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
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125 
# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: dynamo-model-cache
spec:
  accessModes:
    - ReadWriteOnce
  resources:
    requests:
      storage: 100Gi
---
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: frontend
spec:
  services:
    Frontend:
      componentType: frontend
      dynamoNamespace: dynamo
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
---
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: vllm-agg
spec:
  services:
    VllmDecodeWorker:
      pvc:
        create: false
        name: dynamo-model-cache
        mountPoint: /root/.cache/huggingface
      envFromSecret: hf-token-secret
      dynamoNamespace: vllm-agg
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
          workingDir: /workspace/components/backends/vllm
          command:
            - /bin/sh
            - -c
          args:
            - python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B
---
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: agg-qwen
spec:
  backendFramework: vllm
  services:
    EncodeWorker:
      pvc:
        create: false
        name: dynamo-model-cache
        mountPoint: /root/.cache/huggingface
      envFromSecret: hf-token-secret
      dynamoNamespace: agg-qwen
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
          workingDir: /workspace/examples/multimodal
          command:
            - /bin/sh
            - -c
          args:
            - python3 components/encode_worker.py --model Qwen/Qwen2.5-VL-7B-Instruct
    VLMWorker:
      pvc:
        create: false
        name: dynamo-model-cache
        mountPoint: /root/.cache/huggingface
      envFromSecret: hf-token-secret
      dynamoNamespace: agg-qwen
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
          workingDir: /workspace/examples/multimodal
          command:
            - /bin/sh
            - -c
          args:
            - python3 components/worker.py --model Qwen/Qwen2.5-VL-7B-Instruct --worker-type prefill
    Processor:
      pvc:
        create: false
        name: dynamo-model-cache
        mountPoint: /root/.cache/huggingface
      envFromSecret: hf-token-secret
      dynamoNamespace: agg-qwen
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
          workingDir: /workspace/examples/multimodal
          command:
            - /bin/sh
            - -c
          args:
            - 'python3 components/processor.py --model Qwen/Qwen2.5-VL-7B-Instruct --prompt-template "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|><prompt><|im_end|>\n<|im_start|>assistant\n"'