apiVersion: apps.nvidia.com/v1alpha1
kind: NIMCache
metadata:
  name: ngc-nim-cache-universal
spec:
  source:
    ngc:
      modelPuller: gitlab-master.nvidia.com:5005/dl/ai-services/microservices/nim-llm/nim-agnostic:e808bad253c75437582cb1c2a92d6929c5c05e01
      pullSecret: ngc-secret-1
      authSecret: ngc-api-secret-1
      modelEndpoint: "ngc://nvidian/nim-llm-dev/meta-llama3-8b-instruct:hf"
  storage:
    pvc:
      create: true
      storageClass: local-path
      size: "50Gi"
      volumeAccessMode: ReadWriteOnce

apiVersion: apps.nvidia.com/v1alpha1
kind: NIMCache
metadata:
  name: nim-cache-universal
spec:
  source:
    hf:
      endpoint: "https://huggingface.co"
      namespace: "nvidia"
      authSecret: hf-api-secret
      modelPuller: gitlab-master.nvidia.com:5005/dl/ai-services/microservices/nim-llm/nim-agnostic:e808bad253c75437582cb1c2a92d6929c5c05e01
      pullSecret: ngc-secret-1
      modelName: "Llama-3.1-Nemotron-Nano-8B-v1"
  storage:
    pvc:
      create: true
      storageClass: local-path
      size: "50Gi"
      volumeAccessMode: ReadWriteOnce