Release Notes for EGS Version 1.14.0
Release Date: 5th June 2025
The EGS (Elastic GPU Service) platform is an innovative solution designed to optimize GPU utilization and efficiency for your AI projects. EGS leverages the power of Kubernetes to deliver optimized GPU resource management, GPU provisioning and GPU fault identification.
We continue to add new features and enhancements to EGS.
These release notes describe the new changes and enhancements in this version.
Across our documentation, we refer to the workspace as the slice workspace. The two terms are used interchangeably.
What's New 🔈
Cluster Selection for an Inference Endpoint
When deploying an Inference Endpoint, users can choose to send their workload to either a single cluster or multiple clusters based on their specific requirements.
For more information, see:
- Deploy Inference Endpoints from the Admin Portal.
- Deploy Inference Endpoints from the User Portal.
Inference Endpoint Bursting
A new Bursting to Available Clusters field is introduced, allowing users to choose whether they want to enable bursting to available clusters.
- This option is enabled by default.
- Users can uncheck it if they prefer to restrict the workload to their selected clusters only.
For more information, see:
- Deploy Inference Endpoints from the Admin Portal.
- Deploy Inference Endpoints from the User Portal.
Standard Model for Inference Endpoints
The ESG portal now includes a new Standard Model field, allowing users to select different models when deploying an Inference Endpoint. You must configure a ConfigMap to populate the data in the Standard Model dropdown menu.
For more information, see:
- Deploy Inference Endpoints from the Admin Portal.
- Deploy Inference Endpoints from the User Portal.
Custom Pricing
The GPU Inventory page on the EGS Portal now includes a GPU Cost section. Users can customize GPU pricing directly from this interface. After a price is updated, all future cost calculations will automatically use the revised pricing.
For more information, see:
- View GPU Inventory details from the Admin Portal.
- View GPU Inventory details from the User Portal.