Mirantis' k0rdent supports Nebul in on-demand AI inference workloads

Mirantis has revealed that Nebul, a Netherlands-based cloud service provider, has implemented the open-source k0rdent platform to facilitate on-demand Artificial Intelligence (AI) inference workloads. This deployment integrates with NVIDIA technologies to unify various infrastructures, streamlining operations while emphasizing privacy and regulatory compliance.

Nebul focuses on privacy and sovereignty, leveraging its expertise in High performance computing (HPC) and AI technologies. As an NVIDIA elite partner, Nebul employs k0rdent’s native multi-cluster management, which works in conjunction with the NVIDIA Graphics Processing Unit (GPU) Operator and Gcore Everywhere Inference.

The platform supports distributed AI inference across an accelerated infrastructure, enhancing performance and reducing latency. It also allocates processing resources dynamically to meet operational demand while optimizing GPU utilization for efficiency.

“Open source is the enabler for infrastructure to support AI,” said Alex Freedland, co-founder and CEO of Mirantis. “Nebul is demonstrating the enormous potential of open technologies to solve one of the most complex challenges in IT today — delivering AI workloads reliably at scale.”

Launched recently, k0rdent helps manage infrastructure and operational complexity across various environments. It employs automation and centralized policy enforcement, allowing for the deployment of Kubernetes clusters anywhere.

“Our challenge was transitioning our existing infrastructure,” said Arnold Juffer, CEO and founder of Nebul. “Using k0rdent enables us to effectively unify our diverse infrastructure while fully transforming to open source to streamline operations.”

Mirantis and Gcore previously announced a partnership aimed at addressing AI infrastructure challenges. Attendees of KubeCon can learn more about k0rdent and see a demonstration of its AI inference capabilities.