disagg_planner_throughput.yaml 2.03 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
# 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-disagg-planner
spec:
  services:
    Frontend:
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
    Planner:
      componentType: planner
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          command:
          - python3
          - -m
25
          - dynamo.planner
26
          args:
27
28
            - --config
            - '{"environment": "kubernetes", "backend": "vllm", "throughput_adjustment_interval": 60, "profile_results_dir": "/workspace/tests/planner/profiling_results/H200_TP1P_TP1D", "no_correction": true}'
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
    VllmDecodeWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: decode
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
          args:
            - -m
            - dynamo.vllm
            - --model
            - nvidia/Llama-3.1-8B-Instruct-FP8
48
49
            - --disaggregation-mode
            - decode
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
    VllmPrefillWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: prefill
      replicas: 1
      resources:
        limits:
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
          args:
            - -m
            - dynamo.vllm
            - --model
            - nvidia/Llama-3.1-8B-Instruct-FP8
69
70
            - --disaggregation-mode
            - prefill