'Set new application replica for each request

I'm trying to deploy my application on a K8S cluster and expose it with a service. My application receives several video streams and needs to handle each stream with a different replica. Is there a way to scale the application with a new replica for each incoming request? I've found horizontal pod autoscaler but don't know how to configure a metric like this

Anyone can help? Thanks.



Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution Source