nimservice.yaml

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
        celExpressions:
        - (device.attributes["gpu.nvidia.com"].productName.lowerAscii().matches("^.*a100.*$") && device.capacity["gpu.nvidia.com"].memory.compareTo(quantity("40Gi")) >= 0) || (device.attributes["gpu.nvidia.com"].productName.lowerAscii().matches("^.*h100.*$") && device.attributes["gpu.nvidia.com"].driverVersion.compareTo(semver("550.127.8")) >= 0)
  expose:
    service:
      type: ClusterIP
      port: 8000