The autoscaling configuration for custom endpoints misses some configurations in the template, including min and max replica counts, cooldown period and more.
The Prometheus trigger is also missing.
Reference: https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-model-deployment-autoscaling.html#sagemaker-hyperpod-model-deployment-autoscaling-yaml
The problem is that these parameters are completely missing from the template so there is no way to use them with the current CLI.