VAST AI OS will leverage NVIDIA libraries to accelerate both compute and data services for RAG, vector search, real-time SQL and agentic applications
Dubai, UAE – February 26, 2026 – At VAST Forward 2026, VAST Data, the AI Operating System company, announced an end-to-end, fully CUDA-accelerated AI data stack delivered through an expanded collaboration with NVIDIA. With the VAST AI Operating System now running directly on NVIDIA-powered servers, customers can eliminate data bottlenecks across the AI pipeline and deliver ingestion, retrieval, analytics and inference in a single unified platform.
By accelerating both data services and the compute layer as one coherent system, the VAST AI OS eliminates the operational complexity of stitching together separate storage, database and AI infrastructure stacks. The result is a simpler and faster path from experimentation to production for RAG pipelines, agentic systems and continuous AI workloads.
Designed in collaboration with NVIDIA, the VAST CNode-X introduces a new generation of NVIDIA-Certified Systems that transform how AI infrastructure is built and operated. In addition to providing high-performance storage services to NVIDIA GPU-accelerated clusters, the VAST AI OS now runs directly on NVIDIA-powered servers, making these systems first-class infrastructure citizens inside the VAST platform. This architectural shift enables VAST to orchestrate AI pipelines, high-performance analytics, vector search, RAG functions and agent runtimes as a single unified software stack.
New CNode-X servers provide the computing foundation for the VAST AI OS to leverage a wide variety of NVIDIA software libraries and APIs directly within core VAST software services, including the VAST DataEngine and VAST DataBase. These accelerations are embedded deep inside the platform, delivering higher performance, lower latency and improved efficiency across real-time SQL analytics, vector search and retrieval, as well as a wide range of AI inferencing workflows.
“Ten years ago, we set out to build a system that could continuously refine data into intelligence and action,” said Renen Hallak, Founder and CEO of VAST Data. “That future is here. By accelerating both compute and the data paths inside the VAST AI OS with NVIDIA, we are giving customers a faster, simpler way to operationalize retrieval, analytics and agentic workflows as one coherent pipeline so AI can move from pilot to durable production systems.”
“NVIDIA is reinventing every pillar of computing for AI. With VAST Data, we are transforming the storage of AI infrastructure,” said Jensen Huang, Founder and CEO of NVIDIA. “CNode-X is CUDA-accelerated at every layer to give AI agents persistent memory so they can work on complex problems over days or weeks, and eventually years, without forgetting, opening the world to the next frontier of AI.”
With GPU-accelerated VAST CNode-X servers as the foundation, VAST is bringing broad support for NVIDIA-accelerated capabilities inside the VAST AI OS and deploying them within a full-stack software platform that runs and orchestrates AI pipelines, vector search services and production AI workflows. New capabilities include:
· GPU-Native SQL Engine Acceleration for VAST DataBase Analytics Pipelines: VAST is advancing the VAST DataBase to accelerate modern analytics workloads across the full query lifecycle by pairing storage-side intelligence with GPU-accelerated execution. The VAST DataBase query engine combines intelligent data layout, pushdown and filtering to reduce unnecessary I O, while using Sirius, an open-source query engine based on NVIDIA cuDF, for GPU-accelerated SQL execution at the compute layer. Early benchmarking of Sirius shows up to a 44 percent reduction in query time and up to an 80 percent reduction in query cost.
· NVIDIA cuVS for Accelerated Vector Search and Retrieval: By embedding the NVIDIA cuVS library, VAST’s CNode-X brings GPU acceleration to vector search and data clustering for organizations using VAST for scalable vector database services and VAST InsightEngine, built on the NVIDIA AI Data Platform reference design, for production RAG pipelines, improving retrieval latency for real-time, context-rich AI applications.
· NVIDIA Nemotron Models and NVIDIA NIM Microservices for Scalable DataEngine Pipelines: VAST will deploy and support NVIDIA NIM microservices across CNode-X for scalable AI pipelines and is open-sourcing production-ready VAST DataEngine blueprints for AI pipelines targeting video intelligence, enterprise document RAG and genomics research use cases.
· NVIDIA CMX to Accelerate Inference at Scale: VAST supports the NVIDIA Context Memory Storage Platform with cluster configurations that include NVIDIA BlueField-4 DPUs and Spectrum-X Ethernet networking to accelerate access to shared KV cache and lower time to first token for long-context, multi-agent inference. VAST’s Disaggregated Shared Everything architecture enables customers to add enterprise data services without compromising KV retrieval time.
Hardware Choice for Accelerating the VAST AI Operating System
VAST plans to bring CNode-X servers to market through leading OEM partners, including Cisco and Supermicro, enabling customers to procure GPU-accelerated infrastructure through preferred vendors while maintaining a consistent VAST software, support and operational experience.
Through certified configurations delivered with OEM partners, VAST provides a faster and more supportable path to production AI. As enterprise AI pipelines become continuous systems, VAST combines its data platform with full-stack NVIDIA-accelerated computing to deliver high-performance retrieval, analytics and vector search that keep GPUs productive across RAG, real-time analytics and large-scale AI workloads.
“AI does not scale on isolated components. It scales through integrated systems,” said Jeremy Foster, SVP and General Manager, Cisco Compute. “Customers need infrastructure that keeps data secure and tightly aligned with intelligent networking and GPU-accelerated compute for an efficient, production-ready platform.”
“Production AI demands a new level of integration across compute, acceleration and the data platform,” said Charles Liang, President and CEO of Supermicro. “Together with VAST Data and NVIDIA, we are delivering a truly integrated AI Data Platform that removes complexity from enterprise AI and enables organizations to move from experimentation to production faster.”
About VAST Data
VAST Data is the AI Operating System company, powering the next generation of intelligent systems with a unified software infrastructure stack purpose-built to unlock the full potential of AI. The VAST AI OS consolidates foundational data and compute services and agentic execution into one scalable platform, enabling organizations to deploy and coordinate AI agents, reason over real-time data and automate complex workflows at global scale. Built on VAST’s Disaggregated Shared Everything architecture, VAST delivers a parallel distributed system that eliminates tradeoffs between performance, scale, simplicity and resilience.
Learn more at vastdata.com and follow VAST Data on LinkedIn, YouTube and X.
For further details, contact:
va******@*******mc.com
