NOW BUZZING 헤어컬러가 브라운과 오렌지로 쪼개지는 이… · 코치, 85주년에 '낡음'을 미래로 바꾸… · 프레피룩, 왜 더 플라자에서 다시 태어났…◆
NOW BUZZING 헤어컬러가 브라운과 오렌지로 쪼개지는 이… · 코치, 85주년에 '낡음'을 미래로 바꾸… · 프레피룩, 왜 더 플라자에서 다시 태어났…◆
JELIBI
⌕ SUBSCRIBE
SEOUL · DAILY · ISSUE No.327 WE TRIED IT · THE PICK · BEHIND IT 2026.09.30 · WED
JELIBI
⌕ SUB
Beauty Body Gadget Bites Buzz World
HOME/GADGET/BEHIND IT
GADGET BEHIND IT · 5 MIN READ

NVIDIA BlueField-4, 에이전트 AI용 저장소 플랫폼 발표

JD 젤리비 편집국 · 2026.06.12 SHARE · COPY LINK

무슨 발표인가

  • 추론 문맥 메모리 저장 플랫폼 발표
  • 토큰/초·전력 효율 최대 5배 향상
  • 에이전트 AI 장기메모리·멀티턴 대화 지원

원문 (영어)

News Summary: NVIDIA BlueField-4 powers NVIDIA Inference Context Memory Storage Platform, a new kind of AI-native storage infrastructure designed for gigascale inference, to accelerate and scale agentic AI. The new storage processor platform is built for long-context-processing agentic AI systems with lightning-fast long- and short-term memory.

Inference Context Memory Storage Platform extends AI agents’ long-term memory and enables high-bandwidth sharing of context across clusters of rack-scale AI systems — boosting tokens per seconds and power efficiency by up to 5x. Enabled by NVIDIA Spectrum-X Ethernet, extended context memory for multi-turn AI agents improves responsiveness, increases throughput per GPU and supports efficient scaling of agentic inference.

CES — NVIDIA today announced that the NVIDIA BlueField -4 data processor, part of the full-stack NVIDIA BlueField platform, powers 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 5x and delivering up to 5x greater power efficiency compared with traditional storage.

원문: NVIDIA News — "NVIDIA BlueField-4 Powers New Class of AI-Native Storage Infrastructure for the Next Frontier of AI" (2026-06-12) 공식 원문: https://nvidianews.nvidia.com/news/nvidia-bluefield-4-powers-new-class-of-ai-native-storage-infrastructure-for-the-next-frontier-of-ai

#NVIDIA News
THE JELIBI BRIEF

A small team that reads too much internet so you don't have to.

SUBSCRIBE →
GADGET

인스로픽, 안전장치 없이 사이버공격 자동화 모델 공개

GADGET

삼성 6개 계열사, AI 인프라 기업 헬릭스에 10억 달러 투자

GADGET

TBC, AWS와 협력해 신경세포 유래 AI 비디오 모델 출시

← GADGET BEHIND IT

NVIDIA BlueField-4, 에이전트 AI용 저장소 플랫폼 발표

젤리비 편집국·2026.06.12·5 MIN
IN THIS PIECE
무슨 발표인가 원문 (영어)

무슨 발표인가

  • 추론 문맥 메모리 저장 플랫폼 발표
  • 토큰/초·전력 효율 최대 5배 향상
  • 에이전트 AI 장기메모리·멀티턴 대화 지원

원문 (영어)

News Summary: NVIDIA BlueField-4 powers NVIDIA Inference Context Memory Storage Platform, a new kind of AI-native storage infrastructure designed for gigascale inference, to accelerate and scale agentic AI. The new storage processor platform is built for long-context-processing agentic AI systems with lightning-fast long- and short-term memory.

Inference Context Memory Storage Platform extends AI agents’ long-term memory and enables high-bandwidth sharing of context across clusters of rack-scale AI systems — boosting tokens per seconds and power efficiency by up to 5x. Enabled by NVIDIA Spectrum-X Ethernet, extended context memory for multi-turn AI agents improves responsiveness, increases throughput per GPU and supports efficient scaling of agentic inference.

CES — NVIDIA today announced that the NVIDIA BlueField -4 data processor, part of the full-stack NVIDIA BlueField platform, powers 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 5x and delivering up to 5x greater power efficiency compared with traditional storage.

원문: NVIDIA News — "NVIDIA BlueField-4 Powers New Class of AI-Native Storage Infrastructure for the Next Frontier of AI" (2026-06-12) 공식 원문: https://nvidianews.nvidia.com/news/nvidia-bluefield-4-powers-new-class-of-ai-native-storage-infrastructure-for-the-next-frontier-of-ai

#NVIDIA News
THE JELIBI BRIEF

A small team that reads too much internet so you don't have to.

SUBSCRIBE →
MORE IN BEHIND IT
질병관리청, WHO 의료대응수단 네트워크 포럼 참석해 감염병 대응 협력 강화인스로픽, 안전장치 없이 사이버공격 자동화 모델 공개삼성 6개 계열사, AI 인프라 기업 헬릭스에 10억 달러 투자Samsung, 세계 심장의 날 캠페인으로 심장 건강 관리 강조CJ도너스캠프, 아동복지시설 교사 260명 교사교육 실시
THE JELIBI BRIEF

인터넷을 너무 많이 보는 팀이 대신 골라 옵니다.

SUBSCRIBE

바로가기 등록하시면, 더 쉽게 찾아보실 수 있습니다.