NVIDIA Launches BlueField-4 STX Storage Architecture With Broad Industry Adoption

News Summary:

• New NVIDIA STX reference architecture provides up to 5x token throughput and up to 4x energy efficiency with 2x faster data ingestion.
• Early adopters of STX for context memory storage include CoreWeave, Crusoe, IREN, Lambda, Mistral AI, Nebius, Oracle Cloud Infrastructure (OCI) and Vultr.
• Storage providers and manufacturing partners are building infrastructure using NVIDIA modular reference designs to advance agentic AI, including AIC, Cloudian, DDN, Dell Technologies, Everpure, Hitachi Vantara, HPE, IBM, MinIO, NetApp, Nutanix, Supermicro, Quanta Cloud Technology (QCT), VAST Data and WEKA.

GTC-NVIDIA today announced NVIDIA BlueField-4^® STX, a modular reference architecture that enables enterprises, cloud and AI providers to easily deploy accelerated storage infrastructure capable of the long-context reasoning required for agentic AI.

Traditional data centers provide high-capacity, general-purpose storage but lack the responsiveness required for seamless interaction with AI agents that work across many steps, tools and sessions. Agentic AI demands real-time access to data and contextual working memory to keep conversations and tasks fast and coherent. As context grows, traditional storage and data paths can slow AI inference and reduce GPU utilization.

NVIDIA STX allows storage providers to build infrastructure that keeps data close and accessible at scale, so agentic AI factories can deliver higher throughput and responsiveness across inference, training and analytics.

The first rack-scale implementation includes the new NVIDIA CMX™ context memory storage platform, which expands GPU memory with a high-performance context layer for scalable inference and agentic systems - providing up to 5x tokens per second compared with traditional storage.

"Agentic AI is redefining what software can do - and the computing infrastructure behind it must be reinvented to keep pace," said Jensen Huang, founder and CEO of NVIDIA. "AI systems that reason across massive context and continuously learn require a new class of storage. NVIDIA STX reinvents the storage stack, providing a modular foundation for AI-native infrastructure that keeps AI factories operating at peak performance."

STX is accelerated by the NVIDIA Vera Rubin platform and harnesses a new, storage-optimized NVIDIA BlueField-4 processor that combines the NVIDIA Vera CPU with NVIDIA ConnectX^®-9 SuperNIC, together with NVIDIA Spectrum-X™ Ethernet networking, NVIDIA DOCA™ and NVIDIA AI Enterprise software.

The STX architecture also enables 4x higher energy efficiency compared with traditional CPU architectures for high-performance storage and can ingest 2x more pages per second for enterprise AI data.

Storage providers partners codesigning next-generation AI infrastructure based on NVIDIA STX include Cloudian, DDN, Dell Technologies, Everpure, Hitachi Vantara, HPE, IBM, MinIO, NetApp, Nutanix, VAST Data and WEKA.

Manufacturing partners building STX-based systems include AIC, Supermicro and Quanta Cloud Technology (QCT).

Leading AI labs and cloud service providers planning to adopt STX for context memory storage include CoreWeave, Crusoe, IREN, Lambda, Mistral AI, Nebius, OCI and Vultr.

STX-based platforms will be available from partners in the second half of this year.

Watch the GTC keynote from Huang and explore sessions.