k8s-nim-operator/config/samples/nim/llm/dra-auto-creation/example1/nimservice.yaml at bcc5e7e40d6e5d94ab13170dcd503ab486796a6a · varunrsekar/k8s-nim-operator · 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
apiVersion: apps.nvidia.com/v1alpha1
kind: NIMService
metadata:
  name: meta-llama3-8b-instruct
spec:
  image:
    repository: nvcr.io/nim/meta/llama-3.1-8b-instruct
    tag: "1.8.3"
    pullPolicy: IfNotPresent
    pullSecrets:
      - ngc-secret
  authSecret: ngc-api-secret
  storage:
    nimCache:
      name: meta-llama3-8b-instruct
      profile: ''
  replicas: 1
  draResources:
  - claimCreationSpec:
      devices:
      - name: gpu
        deviceClassName: gpu.nvidia.com
        driverName: gpu.nvidia.com
        attributeSelectors:
        - key: index
          op: NotEqual
          value:
            intValue: 0
        - key: driverVersion
          op: GreaterThanOrEqual
          value:
            versionValue: "550.127.8"
        - key: architecture
          op: Equal
          value:
            stringValue: Ampere
        capacitySelectors:
        - key: memory
          op: Equal
          value: 40Gi
  expose:
    service:
      type: ClusterIP
      port: 8000