The new optimized stack unlocks the full power of NVIDIA Vera Rubin for agentic AI and inference in the enterprise

Vultr, the world’s largest privately-held cloud infrastructure company, announced today it is delivering an optimized inference stack on NVIDIA Rubin platform. This latest milestone in NVIDIA and Vultr’s long-standing collaboration yields industry-leading tokenomics to support enterprises with ready-to-deploy composable cloud infrastructure leveraging NVIDIA's optimized open-source model and inference frameworks. Vultr announced immediate availability for full stack NVIDIA AI Enterprise Inference solutions through partner NetApp with planned NVIDIA Vera Rubin support in Q4 2026.

As part of this industry-first solution, Vultr is adopting the NVIDIA Dynamo inference framework and NVIDIA Nemotron model family to accelerate industry-specific AI outcomes and targeted use cases. These powerful open-source resources enable higher throughput and seamless scaling of inference workloads. Combined with Vultr’s high-performance infrastructure, NVIDIA Dynamo and Nemotron accelerate the path to deployment while reducing the cost of inference – a critical barrier to scaling enterprise AI initiatives.

“The rise of agentic AI demands powerful, reliable AI infrastructure and a production-ready full stack to accelerate innovation,” said J.J. Kardwell, CEO of Vultr. “With NVIDIA and our software partners, we are delivering an integrated AI environment that enables enterprises to deploy next-generation models efficiently and at scale on NVIDIA’s Rubin Platform.”

As a Preferred NVIDIA Cloud Partner, Vultr deploys NVIDIA AI infrastructure at any scale, globally. Customers can build once and deploy widely, driving scale and reducing time-to-value for AI applications. The new enterprise inference stack can be deployed on public, private or sovereign clouds, making it suitable for a broad spectrum of enterprise use cases, including those involving highly sensitive data. Vultr and NVIDIA are also working together on NVIDIA NemoClaw — an open source stack that simplifies running OpenClaw always-on assistants, more safely, with a single command. As part of the NVIDIA Agent Toolkit, it installs the NVIDIA OpenShell runtime — a secure environment for running autonomous agents, and open source models like NVIDIA Nemotron.

“Vultr’s global reach and hyperscaler-level capacity make them a powerful partner in this next evolution of the AI era,” said Dave Salvator, Director of Accelerated Computing Products at NVIDIA. “Innovating with Vultr allows us to optimize our robust open-source portfolio for enterprise AI workloads, propelling advancements in agentic AI and reinventing the economics of inference. Unlocking NVIDIA Vera Rubin systems means unlocking the future of the enterprise, where AI takes productivity, efficiency, and quality of service to new heights.”

Further enhancing the stack, Vultr has partnered with NetApp to deliver the resilient, high-performance foundation required for an AI-ready data estate. NetApp’s AFX, a disaggregated data management platform, delivers the performance and scale needed for building modern AI-driven business solutions. When combined with NetApp's AI Data Engine, built on the NVIDIA AI Data Platform reference design, AI services are now accelerated with AI-ready data transformed in-place, secured and performant for enterprise-scale inferencing driving agentic AI workflows.

“Our collaboration with Vultr was founded on a shared mission to help enterprises navigate today’s data management challenges and push the boundaries of AI,” said Syam Nair, Chief Product Officer at NetApp. “In bringing an enterprise-grade data platform delivering GPU-saturating performance with built-in security to this optimized stack for the next generation of AI infrastructure, we’re helping customers leverage AI with agility and deliver business outcomes without compromises.”

Vultr’s expansive global footprint and scaling capabilities have set the standard for enterprise-ready cloud infrastructure solutions. Hundreds of thousands of enterprises and developers across the globe rely on Vultr’s flexible, cost-efficient infrastructure to support their most demanding workloads. With 33 cloud data center regions across six continents, Vultr provides GPU-forward, infrastructure-first solutions with the data residency, security, and accessibility needed to support mission-critical AI workloads, including in highly regulated industries.

To learn more about how Vultr is redefining enterprise AI infrastructure, visit vultr.com.

About Vultr

Vultr is on a mission to make high-performance cloud infrastructure easy to use, affordable, and locally accessible for enterprises and AI innovators around the world. Vultr is trusted by hundreds of thousands of active customers across 185 countries for its flexible, scalable, global Cloud Compute, Cloud GPU, Bare Metal, and Cloud Storage solutions. In December 2024, Vultr announced an equity financing at a $3.5 billion valuation. Founded by David Aninowsky and self-funded for over a decade, Vultr has grown to become the world’s largest privately-held cloud infrastructure company.

Learn more at: www.vultr.com.

View source version on businesswire.com: https://www.businesswire.com/news/home/20260316996077/en/

The new optimized stack unlocks the full power of NVIDIA Vera Rubin for agentic AI and inference in the enterprise