About this Webinar

At OpenNebula, we have been exploring AI integration from different perspectives: enhancing cloud operations using AI-driven approaches and leveraging OpenNebula clouds for AI training and inference.

This webinar introduces how OpenNebula implements “AI as a Service” model for LLMs, providing users with a robust and vendor-neutral foundation for deploying and using the latests LLMs efficiently and simply.

A demo will showcase OpenNebula appliance for Managed Inference, which integrates Ray Serve, a scalable and high-performance model serving framework. This appliance simplifies the deployment of AI workloads by leveraging Ray Serve’s capabilities for efficient inference, enabling organizations to deploy and scale AI models within OpenNebula cloud environments.

What to expect from this webinar?

• How OpenNebula capabilities enable cost-effective and scalable AI workloads.
• Best practices for deploying GPU-accelerated services for AI inference.
• How OpenNebula’s Ray appliance provides efficient LLM model serving.

This webinar will be conducted by Francisco Picolini (Open Source Community Manager), with presentations by Marco Mancini (Principal Technologist for AI and Data Operations), and Carlos Moral Rubio (Senior Technologist).