Release Notes for EGS version 1.10.1
Release Date: 17th January 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.
What's New 🔈​
Inference Endpoints​
The EGS platform now provides a new tab called Inference Endpoints that serves as the operational interface to deploy AI models to users or applications.
The admin can deploy Inference Endpoints. The admin can also manage all the inference endpoints created in an account. A user can view the inference endpoints created by the admin.
To know more, see:
Access the User Portal with an Owner Role-based API Token​
Starting with version 1.10.1, an owner role-based API token generated for a slice also serves as a token to access the User Portal. To know more, see API token. This is in addition to the token that an admin can retrieve for a slice.