small:
  inferenceService:
    resources:
      requests:
        cpu: 2000m
        memory: 4Gi
        nvidia.com/gpu: "1"
      limits:
        cpu: 4000m
        memory: 8Gi
        nvidia.com/gpu: "1"

medium:
  inferenceService:
    resources:
      requests:
        cpu: 4000m
        memory: 8Gi
        nvidia.com/gpu: "1"
      limits:
        cpu: 8000m
        memory: 16Gi
        nvidia.com/gpu: "2"

large:
  inferenceService:
    resources:
      requests:
        cpu: 8000m
        memory: 16Gi
        nvidia.com/gpu: "2"
      limits:
        cpu: 16000m
        memory: 32Gi
        nvidia.com/gpu: "4"