The cloud computing platform Vultr has announced that it will offer an optimized inference stack based on Nvidia’s Rubin Platform. In addition, it has announced the availability of complete NVIDIA AI Enterprise inference solutions, through its partners WWT and NetApp, with support planned for NVIDIA Vera Rubin in the last quarter of 2026.
As part of this solution, Vultr is adopting the NVIDIA Dynamo inference framework and the NVIDIA Nemotron family of models for the acceleration of industry-specific and use-case-specific AI results. These open source resources help improve the performance and scalability of inference workloads. Additionally, combined with Vultr’s high-performance infrastructure, Dynamo and Nemotron accelerate the deployment process and reduce the cost of inference, with the goal of facilitating the scaling of AI initiatives.
Vultr and NVIDIA are also working together on NVIDIA NemoClaw, and as part of the NVIDIA Agent Toolkit, it installs the secure NVIDIA OpenShell execution environment, which can run standalone agents and open source models, such as those in the Nemotron family.
On the other hand, Vultr has partnered with NetApp to offer a high-performance foundation for AI. The agreement they have reached involves the combination of the NetApp AFX disaggregated data management platform with NetApp AI Data Engine, based on the NVIDIA AI Data Platform design. This combination enables the acceleration of AI services with AI-ready data that is transformed directly at the point where it is found, strengthening its security and improving its performance for enterprise-scale inference, thus streamlining agentic AI tasks.
J.J. Kardwell, CEO de Vultrhas highlighted that «The rise of agentic AI requires a powerful and reliable AI infrastructure and a complete, production-ready technology stack that accelerates innovation. Together with NVIDIA and our software partners, we are delivering an integrated AI environment that enables companies to efficiently deploy next-generation models at scale on the NVIDIA Rubin platform.”.
On the part of NVIDIA, Dave Salvator, its Director of Accelerated Computing Productshas commented that «Vultr’s global reach and hyperscaler-level capabilities make them a key partner in this new evolution of the AI era.. Innovating with Vultr allows us to optimize our strong open source portfolio for enterprise AI workloads, driving advances in agentic AI and reinventing the economics of inference. Unlocking NVIDIA Vera Rubin systems means opening the door to the future of the enterprise, where AI takes productivity, efficiency and quality of service to new levels.”
