Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
disagg_xpu_dra.yaml 2.65 KB
Newer Older
Yao Qing's avatar
feat: add Intel XPU deployment templates with Kubernetes DRA support (#7464)  
Yao Qing 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 
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0

apiVersion: resource.k8s.io/v1
kind: ResourceClaimTemplate
metadata:
  name: gpu-template
spec:
  spec:
    devices:
      requests:
        - name: gpu
          exactly:
            deviceClassName: gpu.intel.com
            count: 1
---
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: vllm-disagg-xpu-dra
spec:
  services:
    Frontend:
      envFromSecret: hf-token-secret
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
    VllmDecodeWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: decode
      replicas: 1
      resources:
        requests:
          custom:
            # Increase this value for larger models
            ephemeral-storage: "2Gi"
      extraPodSpec:
        resourceClaims:
          - name: gpu
            resourceClaimTemplateName: gpu-template
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          resources:
            claims:
              - name: gpu
          env:
            - name: VLLM_TARGET_DEVICE
              value: xpu
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
            - -m
            - dynamo.vllm
          args:
            - --model
            - Qwen/Qwen3-0.6B
            - --disaggregation-mode
            - decode
            - --block-size
            - "64"
    VllmPrefillWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: prefill
      replicas: 1
      resources:
        requests:
          custom:
            # Increase this value for larger models
            ephemeral-storage: "2Gi"
      extraPodSpec:
        resourceClaims:
          - name: gpu
            resourceClaimTemplateName: gpu-template
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          resources:
            claims:
              - name: gpu
          env:
            - name: VLLM_TARGET_DEVICE
              value: xpu
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
            - -m
            - dynamo.vllm
          args:
            - --model
            - Qwen/Qwen3-0.6B
            - --disaggregation-mode
            - prefill
            - --kv-transfer-config
            - '{"kv_connector":"NixlConnector","kv_role":"kv_both","kv_buffer_device":"xpu"}'
            - --block-size
            - "64"