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