Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
disagg_router.yaml 5.29 KB
Newer Older
mohammedabdulwahhab's avatar
feat: add crds for vllm and llm examples (#1766)  
mohammedabdulwahhab 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
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152 
# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: disagg-router
spec:
  envs:
    - name: DYN_DEPLOYMENT_CONFIG
      value: '{"Common":{"model":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","block-size":64,"max-model-len":16384,"router":"kv","kv-transfer-config":"{\"kv_connector\":\"DynamoNixlConnector\"}"},"Frontend":{"served_model_name":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","endpoint":"dynamo.Processor.chat/completions","port":8000},"Processor":{"common-configs":["model","block-size","max-model-len","router"]},"Router":{"min-workers":1,"common-configs":["model","block-size","router"]},"VllmWorker":{"max-num-batched-tokens":16384,"remote-prefill":true,"conditional-disagg":true,"max-local-prefill-length":10,"max-prefill-queue-size":2,"tensor-parallel-size":1,"enable-prefix-caching":true,"ServiceArgs":{"workers":1,"resources":{"gpu":"1"}},"common-configs":["model","block-size","max-model-len","router","kv-transfer-config"]},"PrefillWorker":{"max-num-batched-tokens":16384,"ServiceArgs":{"workers":1,"resources":{"gpu":"1"}},"common-configs":["model","block-size","max-model-len","kv-transfer-config"]},"Planner":{"environment":"kubernetes","no-operation":true}}'
  services:
    Frontend:
      dynamoNamespace: llm-disagg-router
      componentType: main
      replicas: 1
      resources:
        requests:
          cpu: "1"
          memory: "2Gi"
        limits:
          cpu: "1"
          memory: "2Gi"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
          workingDir: /workspace/examples/llm
          args:
            - dynamo
            - serve
            - graphs.disagg_router:Frontend
            - --system-app-port
            - "5000"
            - --enable-system-app
            - --use-default-health-checks
            - --service-name
            - Frontend
    Processor:
      dynamoNamespace: llm-disagg-router
      componentType: worker
      replicas: 1
      resources:
        requests:
          cpu: "1"
          memory: "2Gi"
        limits:
          cpu: "1"
          memory: "2Gi"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
          workingDir: /workspace/examples/llm
          args:
            - dynamo
            - serve
            - graphs.disagg_router:Processor
            - --system-app-port
            - "5000"
            - --enable-system-app
            - --use-default-health-checks
            - --service-name
            - Processor
    Router:
      dynamoNamespace: llm-disagg-router
      componentType: worker
      replicas: 1
      resources:
        requests:
          cpu: "1"
          memory: "2Gi"
        limits:
          cpu: "1"
          memory: "2Gi"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
          workingDir: /workspace/examples/llm
          args:
            - dynamo
            - serve
            - graphs.disagg_router:Router
            - --system-app-port
            - "5000"
            - --enable-system-app
            - --use-default-health-checks
            - --service-name
            - Router
    VllmWorker:
      envFromSecret: hf-token-secret
      dynamoNamespace: llm-disagg-router
      replicas: 1
      resources:
        requests:
          cpu: "10"
          memory: "20Gi"
          nvidia.com/gpu: "1"
        limits:
          cpu: "10"
          memory: "20Gi"
          nvidia.com/gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
          workingDir: /workspace/examples/llm
          args:
            - dynamo
            - serve
            - graphs.disagg_router:VllmWorker
            - --system-app-port
            - "5000"
            - --enable-system-app
            - --use-default-health-checks
            - --service-name
            - VllmWorker
    PrefillWorker:
      envFromSecret: hf-token-secret
      dynamoNamespace: llm-disagg-router
      replicas: 1
      resources:
        requests:
          cpu: "10"
          memory: "20Gi"
          nvidia.com/gpu: "1"
        limits:
          cpu: "10"
          memory: "20Gi"
          nvidia.com/gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
          workingDir: /workspace/examples/llm
          args:
            - dynamo
            - serve
            - graphs.disagg_router:PrefillWorker
            - --system-app-port
            - "5000"
            - --enable-system-app
            - --use-default-health-checks
            - --service-name
            - PrefillWorker