Nvidia unveils BlueField-4 STX storage architecture to solve agentic AI data bottleneck

Nvidia launches BlueField-4 STX storage architecture for agentic AI at GTC 2026

Nvidia announced BlueField-4 STX at GTC 2026 on March 16, a modular reference architecture for accelerated storage designed to address the data access bottleneck limiting agentic AI inference. Built around a new storage-optimized BlueField-4 DPU and ConnectX-9 SuperNIC, the platform targets GPU underutilization that occurs when AI agents operating across extended sessions and expanding context windows exceed the throughput of conventional storage paths. Nvidia says STX delivers up to five times the token throughput, four times better energy efficiency, and twice the page ingestion speed compared with traditional CPU-based storage architectures. The specific issue that Nvidia is targeting with STX is KV cache management. During transformer inference, the attention mechanism computes KV pairs for every token in context, which must be stored and retrieved for each subsequent generation step. But these context windows are growing into the hundreds of thousands of tokens, meaning that the KV cache is outgrowing GPU HBM capacity. The usual fallback is to offload to host DRAM or NVMe storage, but both routes pass through the CPU, adding latency that compounds with context length and stalls GPU execution as data transits. STX bypasses the host CPU by routing data through a dedicated accelerated storage layer via RDMA over Spectrum-X Ethernet. BlueField-4 manages NVMe SSDs directly and handles data integrity and encryption for the KV cache, keeping context accessible at the storage processor rather than transit­ing the host. The full stack runs on the Vera Rubin platform and integrates the Vera CPU -- also announced at GTC on March 16 -- alongside ConnectX-9, Spectrum-X Ethernet, DOCA software, and AI Enterprise software. The first rack-scale implementation built on STX is the Nvidia CMX context memory storage platform. Storage and infrastructure vendors co-designing systems based on STX include DDN, Dell Technologies, HPE, IBM, NetApp, and VAST Data, alongside manufacturing partners AIC, Supermicro, and Quanta Cloud Technology. Meanwhile, eight cloud and AI providers -- including CoreWeave, Lambda, Mistral AI, and Oracle Cloud Infrastructure -- committed to early adoption for context memory storage. STX-based platforms are expected from partners in the second half of 2026. "Agentic AI is redefining what software can do -- and the computing infrastructure behind it must be reinvented to keep pace," Jensen Huang, founder and CEO of Nvidia, said at GTC. "AI systems that reason across massive context and continuously learn require a new class of storage." Follow Tom's Hardware on Google News, or add us as a preferred source, to get our latest news, analysis, & reviews in your feeds.

Nvidia BlueField-4 STX adds a context memory layer to storage to close the agentic AI throughput gap

When an AI agent loses context mid-task because traditional storage can't keep pace with inference, it is not a model problem -- it is a storage problem. At GTC 2026, Nvidia announced BlueField-4 STX, a modular reference architecture that inserts a dedicated context memory layer between GPUs and traditional storage, claiming 5x the token throughput, 4x the energy efficiency and 2x the data ingestion speed of conventional CPU-based storage. The bottleneck STX targets is key-value cache data. KV cache is the stored record of what a model has already processed -- the intermediate calculations an LLM saves so it does not have to recompute attention across the entire context on every inference step. It is what allows an agent to maintain coherent working memory across sessions, tool calls and reasoning steps. As context windows grow and agents take more steps, that cache grows with them. When it has to traverse a traditional storage path to get back to the GPU, inference slows and GPU utilization drops. STX is not a product Nvidia sells directly. It is a reference architecture the company is distributing to its storage partner ecosystem so vendors can build AI-native infrastructure around it. STX puts a context memory layer between GPU and disk The architecture is built around a new storage-optimized BlueField-4 processor that combines Nvidia's Vera CPU with the ConnectX-9 SuperNIC. It runs on Spectrum-X Ethernet networking and is programmable through Nvidia's DOCA software platform. The first rack-scale implementation is the Nvidia CMX context memory storage platform. CMX extends GPU memory with a high-performance context layer designed specifically for storing and retrieving KV cache data generated by large language models during inference. Keeping that cache accessible without forcing a round trip through general-purpose storage is what CMX is designed to do. "Traditional data centers provide high-capacity, general-purpose storage, but generally lack the responsiveness required for interaction with AI agents that need to work across many steps, tools and different sessions," Ian Buck, Nvidia's vice president of hyperscale and high-performance computing said in a briefing with press and analysts. In response to a question from VentureBeat, Buck confirmed that STX also ships with a software reference platform alongside the hardware architecture. Nvidia is expanding DOCA to include a new component referred to in the briefing as DOCA Memo. "Our storage providers can leverage the programmability of the BlueField-4 processor to optimize storage for the agentic AI factory," Buck said. "In addition to having a reference rack architecture, we're also providing a reference software platform for them to deliver those innovations and optimizations for their customers." Storage partners building on STX get both a hardware reference design and a software reference platform -- a programmable foundation for context-optimized storage. Nvidia's partner list spans storage incumbents and AI-native cloud providers Storage providers co-designing STX-based infrastructure 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. On the cloud and AI side, CoreWeave, Crusoe, IREN, Lambda, Mistral AI, Nebius, Oracle Cloud Infrastructure and Vultr have all committed to STX for context memory storage. That combination of enterprise storage incumbents and AI-native cloud providers is the signal worth watching. Nvidia is not positioning STX as a specialty product for hyperscalers. It is positioning it as the reference standard for anyone building storage infrastructure that has to serve agentic AI workloads -- which, within the next two to three years, is likely to include most enterprise AI deployments running multi-step inference at scale. STX-based platforms will be available from partners in the second half of 2026. IBM shows what the data layer problem looks like in production IBM sits on both sides of the STX announcement. It is listed as a storage provider co-designing STX-based infrastructure, and Nvidia separately confirmed that it has selected IBM Storage Scale System 6000 -- certified and validated on Nvidia DGX platforms -- as the high-performance storage foundation for its own GPU-native analytics infrastructure. IBM also announced a broader expanded collaboration with Nvidia at GTC, including GPU-accelerated integration between IBM's watsonx.data Presto SQL engine and Nvidia's cuDF library. A production proof of concept with Nestlé put numbers on what that acceleration looks like: a data refresh cycle across the company's Order-to-Cash data mart, covering 186 countries and 44 tables, dropped from 15 minutes to three minutes. IBM reported 83% cost savings and a 30x price-performance improvement. The Nestlé result is a structured analytics workload. It does not directly demonstrate agentic inference performance. But it makes IBM and Nvidia's shared argument concrete: the data layer is where enterprise AI performance is currently constrained, and GPU-accelerating it produces material results in production. Why the storage layer is becoming a first-class infrastructure decision STX is a signal that the storage layer is becoming a first-class concern in enterprise AI infrastructure planning, not an afterthought to GPU procurement. General-purpose NAS and object storage were not designed to serve KV cache data at inference latency requirements. STX-based systems from partners including Dell, HPE, NetApp and VAST Data are what Nvidia is putting forward as the practical alternative, with the DOCA software platform providing the programmability layer to tune storage behavior for specific agentic workloads. The performance claims -- 5x token throughput, 4x energy efficiency, 2x data ingestion -- are measured against traditional CPU-based storage architectures. Nvidia has not specified the exact baseline configuration for those comparisons. Before those numbers drive infrastructure decisions, the baseline is worth pinning down. Platforms are expected from partners in the second half of 2026. Given that most major storage vendors are already co-designing on STX, enterprises evaluating storage refreshes for AI infrastructure in the next 12 months should expect STX-based options to be available from their existing vendor relationships.

Nvidia introduces BlueField-4 STX reference architecture for AI storage systems - SiliconANGLE

Nvidia introduces BlueField-4 STX reference architecture for AI storage systems Nvidia Corp. today launched a reference architecture that hardware makers can use to build storage equipment for artificial intelligence clusters. The BlueField-4 STX made its debut at the company's GTC developer event. "AI systems that reason across massive context and continuously learn require a new class of storage," said Nvidia Chief Executive Officer Jensen Huang. "NVIDIA STX reinvents the storage stack, providing a modular foundation for AI-native infrastructure that keeps AI factories operating at peak performance." The architecture's first building block is the BlueField-4 data processing unit, or DPU, that Nvidia unveiled in January. A DPU offloads infrastructure management tasks from a server's main processor to leave more computing capacity for applications. The BlueField-4 handles tasks such as processing data traffic between GPUs and flash storage. According to Nvidia, the BlueField-4 STX also includes its Spectrum-X Ethernet switches and ConnectX-9 SuperNICs. Usually, the data that a server fetches from storage has to pass through its central processing unit and operating system. Spectrum-X and ConnectX-9 support a technology called RDMA that skips those pit stops, which speeds up the flow of traffic. Nvidia says that BlueField-4 STX can process tokens, units of data used by AI models, up to 5 times faster than earlier storage architectures. The company also expects a fourfold improvement in energy-efficiency. The first rack-scale implementation of the BlueField-4 STX architecture is a storage system design called CMX. It's optimized to hold key-value caches, data structures that large language models use to store information. LLMs include an attention mechanism that analyzes each prompt, determines which of its elements are most important and prioritizes them. Along the way, the attention mechanism works turns the contents of the prompt into mathematical objects called vectors. It uses two main types of vectors: keys that help the LLM find information and values that hold the information. CMX stores an AI cluster's key-value cache in high-speed flash storage. BlueField-4 chips offload key data management tasks from the host cluster's CPUs to boost performance. According to Nvidia, CMX also speeds up AI workloads in other ways. Storage systems use multiple hardware-intensive algorithms to reduce the risk of data loss. CMX doesn't run those algorithms on the KV cache that it holds, which avoids the associated hardware overhead. The system can skip that step because a KV cache often doesn't require the same data loss protection as standard business records. The information in a KV cache is relatively easy to recover and is usually only retained for a short amount of time before it's deleted.