From Bare Metal to LLMs: Build your NVIDIA AI Factory with OpenNebula

In this screencast, we demonstrate how to build an NVIDIA AI Factory with OpenNebula and OneLLM, turning GPU capacity into ready-to-use LLM inference services that users and applications can access through an API.

You’ll learn how to:
– Install OneLLM on an existing GPU-enabled Kubernetes cluster
– Deploy an LLM and expose it as an inference service
– Share the service with users and generate API keys
– Test inference requests in the Playground
– Visualize service usage and costs

#NVIDIA #AIFactory #LLM #OpenNebula