Netherlands-based private cloud service provider Nebul has deployed Mirantis‘ open-source k0rdent platform to offer on-demand AI inference services, enabling customers to efficiently run AI workloads. The Kubernetes-native multi-cluster management solution, maintained by Mirantis, simplifies operational complexity while optimizing GPU utilization.

Nebul, known for its focus on privacy, sovereignty, and high-performance computing, integrates k0rdent with NVIDIA GPU Operator and Gcore Everywhere Inference to support distributed AI inference across its infrastructure. This setup ensures low-latency performance and dynamic resource provisioning, making AI inference more scalable and efficient.

“We believe open source is the enabler for infrastructure to support AI,” said Alex Freedland, co-founder and CEO, Mirantis, the maintainer of k0rdent. “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 last month, k0rdent helps platform engineers manage infrastructure across cloud, on-premises, and edge environments. It simplifies maintenance through declarative automation, centralized policy enforcement, and production-ready templates. The platform is fully composable and integrates with Cluster API, allowing Kubernetes clusters to be created and managed anywhere.

“As demand for AI services grows, our challenge was transitioning our existing infrastructure,” said Arnold Juffer, CEO and founder at Nebul. “Using k0rdent enables us to effectively unify our diverse infrastructure across OpenStack, bare metal Kubernetes, while sunsetting the VMware technology stack and fully transforming to open source to streamline operations and accelerate our shift to Inference-as-a-Service for enterprise customers. Now, they can bring their trained AI model to their data and just run it with assurance of privacy and sovereignty in accordance with regulations. It’s as simple as that.”

Gcore’s Edge AI product director, Seva Vayner, highlighted that Nebul’s use of AI inference infrastructure ensures AI applications meet cost and performance requirements. Gcore’s Everywhere Inference platform facilitates seamless AI workload deployment with Smart Routing to send inference tasks to the nearest GPUs for optimal efficiency.

Mirantis and Gcore announced their collaboration at NVIDIA GTC on March 18. Attendees at KubeCon London (April 2-4, 2025) can learn more about k0rdent and view AI inference demos at Mirantis booth N331 and Cloud Native + Kubernetes AI Day Europe (April 1) at Mirantis’ table in N10 area, Level 1.