Avesha Resources / Blogs
Uma Tammanagoudar
Staff Technical Writer
We are thrilled to announce the official release of EGS version 1.14.0, now available as of June 5, 2025.
Avesha EGS stands for Elastic GPU Service, a platform developed by Avesha to optimize the management of GPU and CPU resources for AI and machine learning workloads.
Avesha EGS is designed to address the challenges of managing GPU-intensive workloads, offering a solution that enhances efficiency, scalability, and cost-effectiveness in AI operations.
When deploying an Inference Endpoint, users now have the flexibility to:
This feature enables users to customize deployments to fit their specific requirements seamlessly.
We’ve introduced a new Bursting to Available Clusters option to maximize scalability:
This enhancement ensures a balance between resource scalability and user-defined workload boundaries.
The EGS portal now features a Standard Model field, simplifying the deployment of Inference Endpoints:
This feature streamlines deployment and ensures consistency across Inference Endpoints.
Manage costs effectively with the new GPU Cost section in the GPU Inventory page:
This update empowers users to maintain precise control over GPU-related expenses.
EGS now supports AMD GPUs in beta, in addition to existing NVIDIA GPU support:
Note: Certain features, such as pricing and dashboard monitoring for AMD GPUs, are currently unavailable in this release.
These updates highlight our ongoing commitment to providing enhanced insights and greater control for our users. Refer to the latest documentation for detailed guidance on utilizing these enhancements.
We value your feedback and are always here to assist you. Whether you have questions or ideas for improvement, don’t hesitate to reach out!
The Missing Layers in AI Agents: Observability + Evaluation
Unlocking Retail Magic with Elastic GPU Service (EGS): Elevating AI, ML, and Inferencing Workloads
Unlocking the Power of Enterprise AI: Nutanix and Avesha's Elastic GPU Service for Scalable Inferencing
Maximizing AI Infrastructure ROI with Elastic GPU Service Bursting: A Business Use Case
Copied