NVIDIA 协同设计五招提升 AI 工厂每字节价值
原标题：Five Ways NVIDIA Co-Design Maximizes the Value of Every Byte in the AI Factory
AI 摘要
NVIDIA 在技术博客中介绍其 AI 工厂的协同设计方法，通过 NVFP4 低精度格式、宽专家并行（Wide-EP）、KV 缓存复用与 Dynamo 分布式服务等手段，提升每字节内存的有效利用率。文章称在 SemiAnalysis AgentX 基准上，Vera Rubin NVL72 在每用户 160 tokens/s 下每兆瓦吞吐量可达 GB300 NVL72 的 30 倍。
正文节选
In an AI factory, high bandwidth memory (HBM)is the fastest, most expensive, and most contested memory tier. Every byte spent on a redundant weight copy, an idle session’s KV cache, or a recomputed prefix is a byte that is not being used to produce tokens. The question is no longer how much memory a GPU has, but how much useful work each byte delivers. The generational data in Figure 1 below shows why. From GB300 to NVIDIA Rubin, capacity held at 288 GB while bandwidth rose to 19.2 TB/s. agentic