dynamo/recipes/nemotron-3-super-fp8/sglang/disagg/deploy.yaml at main · GavinZhu-GMI/dynamo · GitHub

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
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Disaggregated SGLang deployment: prefill/decode split with nixl KV transfer.
# Tested with dynamo 1.0 (SGLang 0.5.9).
#
# Uses TP=2 per worker (prefill: 2 GPUs, decode: 2 GPUs) for a total of 4 GPUs.
# KV cache is transferred between workers via nixl (GPU-direct).
#
# NOT working on dynamo 0.9.1 — same blocking bugs as sglang/agg.
#
# Known issue: Prefill warmup logs a non-blocking warning:
#   "Prefill warmup failed: 'SamplingParams' object is not subscriptable"
# This does not affect functionality.
#
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: nemotron-super-fp8-sglang-disagg
spec:
  backendFramework: sglang
  envs:
    - name: HF_HOME
      value: /opt/models
  pvcs:
    - name: model-cache
      create: false
  services:
    Frontend:
      componentType: frontend
      replicas: 1
      volumeMounts:
        - name: model-cache
          mountPoint: /opt/models
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.2.0
          command:
            - /bin/sh
            - -c
          args:
            - python3 -m dynamo.frontend --router-mode kv --no-kv-events --http-port 8000
    prefill:
      componentType: worker
      subComponentType: prefill
      envFromSecret: hf-token-secret
      replicas: 1
      resources:
        limits:
          gpu: "2"
        requests:
          gpu: "2"
      volumeMounts:
        - name: model-cache
          mountPoint: /opt/models
      sharedMemory:
        size: 16Gi
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.2.0
          workingDir: /workspace
          command:
            - python3
            - -m
            - dynamo.sglang
          args:
            - --model-path
            - nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
            - --served-model-name
            - nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
            - --tp
            - "2"
            - --trust-remote-code
            - --disaggregation-mode
            - prefill
            - --disaggregation-bootstrap-port
            - "12345"
            - --disaggregation-transfer-backend
            - nixl
            - --host
            - 0.0.0.0
            - --dyn-tool-call-parser
            - nemotron_nano
            - --dyn-reasoning-parser
            - nemotron_nano
    decode:
      componentType: worker
      subComponentType: decode
      envFromSecret: hf-token-secret
      replicas: 1
      resources:
        limits:
          gpu: "2"
        requests:
          gpu: "2"
      volumeMounts:
        - name: model-cache
          mountPoint: /opt/models
      sharedMemory:
        size: 16Gi
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.2.0
          workingDir: /workspace
          command:
            - python3
            - -m
            - dynamo.sglang
          args:
            - --model-path
            - nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
            - --served-model-name
            - nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
            - --tp
            - "2"
            - --trust-remote-code
            - --disaggregation-mode
            - decode
            - --disaggregation-bootstrap-port
            - "12345"
            - --disaggregation-transfer-backend
            - nixl
            - --host
            - 0.0.0.0
            - --dyn-tool-call-parser
            - nemotron_nano
            - --dyn-reasoning-parser
            - nemotron_nano