Nvidia said the BlueField-4 data processor powers the new Nvidia Inference Context Memory Storage Platform, a new class of AI native storage infrastructure for the next frontier of AI.
As AI models scale to trillions of parameters and multistep reasoning, they generate vast amounts of context data — represented by a key-value (KV) cache, critical for accuracy, user experience and continuity.
A KV cache cannot be stored on GPUs long-term, as this would create a bottleneck for real-time inference in multi-agent systems. AI-native applications require a new kind of scalable infrastructure to store and share this data.
Nvidia Inference Context Memory Storage Platform provides the infrastructure for context memory by extending GPU memory capacity, enabling high-speed sharing across nodes, boosting tokens per seconds by up to five times and delivering up to five times greater power efficiency compared with traditional storage.
“AI is revolutionizing the entire computing stack — and now, storage,” said Jensen Huang, CEO of Nvidia, in a statement. “AI is no longer about one-shot chatbots but intelligent collaborators that understand the physical world, reason over long horizons, stay grounded in facts, use tools to do real work, and retain both short-and long-term memory.”
Huang added, “With BlueField-4, Nvidia and our software and hardware partners are reinventing the storage stack for the next frontier of AI.”
Nvidia Inference Context Memory Storage Platform boosts KV cache capacity and
accelerates the sharing of context across clusters of rack-scale AI systems, while
persistent context for multi-turn AI agents improves responsiveness, increases AI
factory throughput and supports efficient scaling of long-context, multi-agent
inference.
Key capabilities of the Nvidia BlueField-4-powered platform include:
● Nvidia Rubin cluster-level KV cache capacity, delivering the scale and efficiency required for long-context, multi-turn agentic inference.
● Up to five times greater power efficiency than traditional storage.
● Smart, accelerated sharing of KV cache across AI nodes, enabled by the Nvidia DOCA framework and tightly integrated with the Nvidia NIXL library and Nvidia Dynamo software to maximize tokens per second, reduce time to first token and improve multi-turn responsiveness.
● Hardware-accelerated KV cache placement managed by Nvidia BlueField-4 eliminates metadata overhead, reduces data movement and ensures secure, isolated access from the GPU nodes.
● Efficient data sharing and retrieval enabled by Nvidia Spectrum-X Ethernet serves as the high-performance network fabric for RDMA-based access to AI-native KV cache.
Storage innovators including AIC, Cloudian, DDN, Dell Technologies, HPE, Hitachi Vantara, IBM, Nutanix, Pure Storage, Supermicro, VAST Data and WEKA are among the first building next-generation AI storage platforms with BlueField-4, which will be available in the second half of 2026.