DDN Infinia helps Nebul reuse model context across its NVIDIA-powered AI cloud, with testing showing nearly 10x faster token responses

DDN, the global leader in AI and data intelligence solutions, announced today at GTC Berlin 2026 that European AI cloud provider Nebul is using DDN Infinia to accelerate AI inference for sovereign workloads across its NVIDIA-powered infrastructure. Specifically, DDN Infinia is being used to store and reuse key-value (KV) cache, reducing the GPU work required to serve AI models.

In testing, DDN helped Nebul sovereign AI workloads find answers faster at a lower cost:

• Nearly 10x faster time to first token with DDN Infinia than Nebul’s own cache on CPU and memory.
• Up to 5x faster token responses than alternative solutions.
• 2.5x more input tokens per second from the same GPUs.
• Nearly 60% lower cost per million input tokens, by reloading context instead of recomputing it.

Testing covered workloads ranging from short prompts to large-token contexts under concurrent demand. Nebul measured results on its own platforms, with the same eight GPUs, model and workloads on both sides.

As AI moves into production, inference performance increasingly depends on how efficiently infrastructure can preserve and reuse work GPUs have already completed. Infinia stores KV cache so it can be accessed across the GPU fleet rather than remaining tied to a single GPU server. If a GPU is replaced or a workload is rescheduled, previously generated context can be restored, provided the key remains available, rather than rebuilt from scratch.

“Every time a GPU rebuilds context it has already processed, it is spending cycles repeating work,” said Alex Bouzari, CEO and Co-Founder at DDN. “By making that context available across Nebul’s GPU fleet, Infinia helps deliver faster inference and more productive use of GPU capacity while keeping data within the sovereign environment.”

Keeping AI Context Available Across the GPU Fleet

DDN Infinia extends Nebul’s data controls to the KV cache used during inference. Tenant, subtenant and dataset scope remain attached to the stored context, while cache capacity can be managed without interrupting inference.

In multi-tenant environments, DDN Infinia helps Nebul:

• Restore model context across the GPU fleet: Infinia stores KV blocks outside individual GPU servers so previously generated context can be restored when the key remains available.
• Keep tenant data isolated: Tenant, subtenant and dataset scope remain part of the key namespace so saved context stays isolated between tenants.
• Manage cache pressure without stopping inference: Infinia applies eviction policies at the dataset and tenant level as capacity fills, allowing inference to continue while older cache data is removed.

“AI sovereignty should not come at the expense of performance,” said Arnold Juffer, CEO of Nebul. “With DDN Infinia, we can reuse model context across our GPU infrastructure instead of spending valuable GPU cycles recomputing it. That makes inference faster and more efficient while keeping the complete AI workload within the sovereign environment.”

Supporting Sovereign AI Workloads in Enterprise Environments

Nebul’s customers illustrate the types of regulated and proprietary AI workloads driving demand for sovereign AI infrastructure.

Netherlands-based Centric, a leading European IT and software company whose solutions support approximately 70% of Dutch municipalities, uses Nebul to run sovereign AI model inference with enterprise-grade security and observability. By keeping AI workloads and data within Nebul’s European infrastructure, Centric can integrate AI into its software and services while maintaining the control, security and operational visibility required for public-sector environments.

Utrecht-based Leukeleu runs its private AI assistant, SureGPT, on Nebul while keeping each customer’s data under that customer’s control. SureGPT is designed for organizations that want to use AI across internal documents such as board strategies, financial models, product roadmaps and other proprietary information while keeping each customer’s data under that customer’s control.

For more information about DDN Infinia, visit www.ddn.com.

About DDN

DDN is the world’s leading provider of AI data storage and data management platforms, powering over 20 years of innovation across HPC, enterprise, and the largest AI deployments on Earth. With its EXA, Infinia, and intelligent data management platforms, DDN delivers unmatched performance, scale, and business value for customers building next-generation AI factories, hyperscale clouds, and Sovereign AI initiatives. DDN is the trusted partner for thousands of the world’s most data-intensive organizations, including the leading national labs, research institutions, enterprises, hyperscalers, financial firms, and autonomous vehicle innovators. For more information, visit www.ddn.com.

About Nebul

Nebul is Europe's Intelligent Cloud: an integrated AI and cloud platform that brings intelligence, infrastructure, and delivery together. The company helps organizations turn their data, knowledge and expertise into intelligence they own and control. As an NVIDIA Elite Partner, Nebul operates SuperCluster infrastructure built on NVIDIA accelerated computing, designed for demanding training and inference workloads. It combines this with models, data capabilities, AI applications and engineering support, taking customers from implementation to production and sustained use. Nebul is built and operated in Europe. Open to the world. For more information: nebul.com

Follow Nebul: LinkedIn, X, and YouTube

Follow DDN: LinkedIn, X, and YouTube

View source version on businesswire.com: https://www.businesswire.com/news/home/20261021088481/en/