Repuse Lab refuse to follow
2026.09.05 Search
repuserepuse
← Tech Lab 2026-03-24 Format · Spec Sheet Record No. 1359 5 min read
Index
무슨 발표인가원문 (영어)
Share KakaoXLink
Tech Lab · Spec Sheet

NVIDIA STX 스토리지, 5배 토큰 처리량·4배 에너지 효율

Spec SheetMeasured
DeskJuwon
FormatSpec Sheet
Checked2026-03-24
StatusDesk verified

무슨 발표인가

원문 (영어)

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.

원문: NVIDIA News — "NVIDIA Launches BlueField-4 STX Storage Architecture With Broad Industry Adoption" (2026-03-24) 공식 원문: https://nvidianews.nvidia.com/news/nvidia-launches-bluefield-4-stx-storage-architecture-with-broad-industry-adoption

#NVIDIA News
Repuse Lab · 2026-03-24 · © 2026
무단전재 및 재배포 금지
Related records
Spec Sheet 1340
Tech Lab 구글 AI, 멸종위기 종 13개 유전체 정보 보존 지원
Spec Sheet 1358
Tech Lab Meta-Arm, AI 데이터센터용 CPU Arm AGI 공동 개발
Spec Sheet 1341
Tech Lab 구글, 애틀란타 미드타운에 19층 규모 신사무실 개설
repuserepuse
never refuse your vibe. just repuse.
Subscribe
repuserepuse
© 2026 Repuse Lab Cloud Dancer · Fresh Purple · Deep Violet