Release Notes for Smart Scaler Version 2.18.0
Release Date: 6th February 2026
Smart Scaler solves the problem of runaway costs of Kubernetes clusters that are heavily over-provisioned to compensate for the reactive and time consuming tuning required for vanilla HPA.
We continue to add new features and enhancements to Smart Scaler.
What's New 🔈​
EGS Serverless 
​
We have introduced a new Inference SaaS service called EGS Serverless, which you can use to deploy your AI or ML model without managing any infrastructure. It lets you focus on your model, while the service handles all operational overhead. You simply deploy the model and start sending inference requests through a ready-to-use endpoint.
This feature is currently in beta, and its performance, and behavior may change without prior notice.
For more information, see Use EGS Serverless.
User Experience Enhancements​
We have revamped the SaaS management console and grouped the features related to CPU workloads under CPU Scaling in the left sidebar.
For more information, see Manage CPU Workloads.