# KServe Custom Values
inferenceService:
  name: "custom-huggingface-model"
  
  model:
    args:
      - --backend=vllm
      - --model_name=llama-2-7b
      - --dtype=float16
    storageUri: "pvc://custom-model-volume/llama-2-7b"
  
  resources:
    limits:
      cpu: "8"
      memory: 16Gi
      nvidia.com/gpu: "1"
    requests:
      cpu: "4"
      memory: 8Gi
      nvidia.com/gpu: "1"

ingress:
  annotations:
    cert-manager.io/cluster-issuer: "root-ca-issuer"
  host:
    domain: "kserve.example.com"
  tls:
    secretName: custom-kserve-tls