Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
disagg_kvbm_tp2.yaml 2.2 KB
Newer Older
Ziqi Fan's avatar
chore: add sample KVBM related k8s deployment manifests (#3523)  
Ziqi Fan 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 
# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0

apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: vllm-disagg-kvbm-tp2
spec:
  services:
    Frontend:
      dynamoNamespace: vllm-disagg-kvbm-tp2
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
    VllmDecodeWorker:
      dynamoNamespace: vllm-disagg-kvbm-tp2
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        requests:
          gpu: "2"
        limits:
          gpu: "2"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          workingDir: /workspace/components/backends/vllm
          command:
          - python3
          - -m
          - dynamo.vllm
          args:
            - --model
            - Qwen/Qwen3-8B
            - --gpu-memory-utilization
            - "0.23"
            - --disable-log-requests
            - --max-model-len
            - "32000"
            - --enforce-eager
            - --tensor-parallel-size
            - "2"
    VllmPrefillWorker:
      dynamoNamespace: vllm-disagg-kvbm-tp2
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        requests:
          gpu: "2"
          memory: "200Gi"
        limits:
          gpu: "2"
          memory: "250Gi"
      envs:
        - name: DYN_KVBM_CPU_CACHE_GB
          value: "100"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          workingDir: /workspace/components/backends/vllm
          command:
          - python3
          - -m
          - dynamo.vllm
          args:
            - --model
            - Qwen/Qwen3-8B
            - --is-prefill-worker
            - --gpu-memory-utilization
            - "0.23"
            - --disable-log-requests
            - --max-model-len
            - "32000"
            - --enforce-eager
            - --connector
            - kvbm
            - nixl
            - --tensor-parallel-size
            - "2"