scaling-policy.json

{
  "TargetValue": 3.0,
  "CustomizedMetricSpecification": {
    "MetricName": "ApproximateBacklogSizePerInstance",
    "Namespace": "AWS/SageMaker",
    "Dimensions": [
      {"Name": "EndpointName", "Value": "medgemma-vllm-endpoint"}
    ],
    "Statistic": "Average"
  },
  "ScaleInCooldown": 300,
  "ScaleOutCooldown": 60
}