dynamo/recipes/qwen3-32b-fp8/vllm/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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
# 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: qwen3-32b-fp8-vllm-disagg
spec:
  backendFramework: vllm
  pvcs:
    - name: model-cache
      create: false
  services:
    Frontend:
      componentType: frontend
      volumeMounts:
        - name: model-cache
          mountPoint: /opt/models
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0
          workingDir: /workspace/examples/backends/vllm
      envs:
        - name: HF_HOME
          value: /opt/models
      replicas: 1
    VllmPrefillWorker:
      componentType: worker
      subComponentType: prefill
      envFromSecret: hf-token-secret
      volumeMounts:
        - name: model-cache
          mountPoint: /opt/models
      sharedMemory:
        size: 40Gi
      extraPodSpec:
        affinity:
          podAffinity:
            preferredDuringSchedulingIgnoredDuringExecution:
            - weight: 100
              podAffinityTerm:
                labelSelector:
                  matchExpressions:
                  - key: nvidia.com/dynamo-component-type
                    operator: In
                    values:
                    - worker
                topologyKey: kubernetes.io/hostname
        mainContainer:
          env:
            - name: SERVED_MODEL_NAME
              value: "Qwen/Qwen3-32B-FP8"
            - name: MODEL_PATH
              value: "Qwen/Qwen3-32B-FP8"
            - name: HF_HOME
              value: /opt/models
            - name: UCX_TLS
              value: "rc_x,rc,cuda_copy,cuda_ipc"
            - name: UCX_NET_DEVICES
              value: "mlx5_0:1"
            - name: UCX_IB_ADDR_TYPE
              value: "eth"
            - name: UCX_RNDV_SCHEME
              value: "get_zcopy"
            - name: UCX_RNDV_THRESH
              value: "0"
          args:
          - |
            ulimit -l unlimited && python3 -m dynamo.vllm \
              --model $MODEL_PATH \
              --served-model-name $SERVED_MODEL_NAME \
              --tensor-parallel-size 2 \
              --data-parallel-size 1 \
              --disaggregation-mode prefill \
              --kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both"}' \
              --gpu-memory-utilization 0.90 \
              --max-model-len 8192 \
              --no-enable-prefix-caching \
              --block-size 128
          command:
          - /bin/sh
          - -c
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0
          workingDir: /workspace/examples/backends/vllm
          securityContext:
            runAsUser: 0
            capabilities:
              add:
                - IPC_LOCK
                - SYS_RESOURCE
      replicas: 2
      resources:
        limits:
          gpu: "2"
          custom:
            rdma/ib: "2"
        requests:
          gpu: "2"
          custom:
            rdma/ib: "2"
    VllmDecodeWorker:
      componentType: worker
      subComponentType: decode
      envFromSecret: hf-token-secret
      volumeMounts:
        - name: model-cache
          mountPoint: /opt/models
      sharedMemory:
        size: 40Gi
      extraPodSpec:
        affinity:
          podAffinity:
            preferredDuringSchedulingIgnoredDuringExecution:
            - weight: 100
              podAffinityTerm:
                labelSelector:
                  matchExpressions:
                  - key: nvidia.com/dynamo-component-type
                    operator: In
                    values:
                    - worker
                topologyKey: kubernetes.io/hostname
        mainContainer:
          env:
            - name: SERVED_MODEL_NAME
              value: "Qwen/Qwen3-32B-FP8"
            - name: MODEL_PATH
              value: "Qwen/Qwen3-32B-FP8"
            - name: HF_HOME
              value: /opt/models
            - name: UCX_TLS
              value: "rc_x,rc,cuda_copy,cuda_ipc"
            - name: UCX_NET_DEVICES
              value: "mlx5_0:1"
            - name: UCX_IB_ADDR_TYPE
              value: "eth"
            - name: UCX_RNDV_SCHEME
              value: "get_zcopy"
            - name: UCX_RNDV_THRESH
              value: "0"
          args:
          - |
            ulimit -l unlimited && python3 -m dynamo.vllm \
              --model $MODEL_PATH \
              --served-model-name $SERVED_MODEL_NAME \
              --tensor-parallel-size 4 \
              --data-parallel-size 1 \
              --kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both"}' \
              --gpu-memory-utilization 0.90 \
              --max-model-len 8192 \
              --no-enable-prefix-caching \
              --block-size 128
          command:
          - /bin/sh
          - -c
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0
          workingDir: /workspace/examples/backends/vllm
          securityContext:
            runAsUser: 0
            capabilities:
              add:
                - IPC_LOCK
                - SYS_RESOURCE
      replicas: 1
      resources:
        limits:
          gpu: "4"
          custom:
            rdma/ib: "2"
        requests:
          gpu: "4"
          custom:
            rdma/ib: "2"