sagemaker auto scaling scaling; https://docs.aws.amazon.com/sagemaker/latest/dg/endpoint-auto-scaling-add-code-define.html

sagemaker_scaling.sh

aws application-autoscaling register-scalable-target --region REGION \
    --service-namespace sagemaker \
    --resource-id endpoint/ENDPOINT_NAME/variant/VARIANT_NAME \
    --scalable-dimension sagemaker:variant:DesiredInstanceCount \
    --min-capacity MIN_VALUE \
    --max-capacity MAX_VALUE
    
    
target_tracking_json='{"TargetValue": SCALING_VALUE, "PredefinedMetricSpecification": {"PredefinedMetricType": "SageMakerVariantInvocationsPerInstance"}}'
echo $target_tracking_json > target_tracking_scaling_policy.json

aws application-autoscaling put-scaling-policy --region REGION \
      --policy-name SageMakerEndpointInvocationScalingPolicy \
      --service-namespace sagemaker \
      --resource-id endpoint/ENDPOINT_NAME/variant/VARIANT_NAME \
      --scalable-dimension sagemaker:variant:DesiredInstanceCount \
      --policy-type TargetTrackingScaling \
      --target-tracking-scaling-policy-configuration file://target_tracking_scaling_policy.json
      
      
aws application-autoscaling describe-scaling-policyies --service-namespace sagemaker