At VAST Forward 2026, VAST Data 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 & CEO of VAST Data. “That future is here. By accelerating both compute and the data paths inside the VAST AI OS with NVIDIA, we’re giving customers a faster, simpler way to operationalise 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’re transforming the storage of AI infrastructure,” said Jensen Huang, Founder and CEO, 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.”
Watch this video with Jensen Huang, Founder & CEO, NVIDIA at VAST Forward on the Future of Data Infrastructure.
With new GPU-accelerated VAST CNode-X servers as the foundation, VAST is bringing together broad support for NVIDIA-accelerated capabilities inside the VAST AI OS and deploys them within a full-stack software platform that runs and orchestrates AI pipelines, vector search services, and production AI pipelines. 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 that 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. NVIDIA cuDF is a library for accelerating structured data analytics. This complementary approach accelerates both what happens before data reaches compute and the compute itself, delivering a database that is simultaneously storage-optimised and GPU-accelerated. Early benchmarking of Sirius shows up to a 44 per cent reduction in query time and up to an 80 per cent reduction in query cost.
- NVIDIA cuVS for accelerated vector search and retrieval: By embedding NVIDIA cuVS library, VAST’s CNode-X brings GPU acceleration to vector search and data clustering for organisations using VAST for scalable vector database services and VAST InsightEngine, built on the NVIDIA AI Data Platform reference design, for the production RAG pipeline, improving retrieval latency for real-time, context-rich AI applications.
- NVIDIA Nemotron models and NVIDIA NIM microservices for scalable dataEngine pipelines: VAST will now deploy and support NVIDIA NIM microservices across CNode-X for scalable AI pipelines and is open-sourcing production-ready VAST DateEngine blueprints for AI pipelines targeting video intelligence, enterprise document RAG, and genomics research use-cases.
- NVIDIA CMX to accelerate inference at scale: VAST supports shared KV cache and lower time-to-first token for long-context, multi-agent inference. This gives agents access to memory across the entire pod. VAST’s Disaggregated Shared Everything (DASE) architecture provides the additional advantage of enabling customers to optionally add in enterprise data services out of band without compromising on 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 their 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 doesn’t 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. Cisco’s collaboration with partners like VAST and NVIDIA is delivering the enterprise-ready foundation organisations need to help securely scale AI with performance, resilience, and control.”
“Production AI demands a new level of integration across compute, acceleration, and the data platform,” said Charles Liang, President and CEO, Supermicro. “Together with VAST Data and NVIDIA, we’re delivering a truly integrated AI Data Platform that removes complexity from enterprise AI. By bringing high-performance compute, scalable data infrastructure, and intelligent software together as one solution, we’re enabling organisations to move from experimentation to production faster and unlock real business value from AI.”
Discussion about this post