新闻
NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt
NVIDIA Developer · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- NVIDIA's Vera Rubin GPU achieves 30x higher throughput per megawatt than Blackwell GB300 on agentic AI workloads using the AgentX benchmark.
- 为何重要
- Data center operators evaluating infrastructure for multi-step AI agent inference with long context and tool use should consider these efficiency metrics.
- 注意
- Vera Rubin results are pending SemiAnalysis review. AgentX replays recorded sessions; real production patterns may differ from the benchmark's captured traffic.
收听本摘要
- agent
- agentic
- rag
- prompt
- inference
还有谁报道了
- Solving Agentic AI Fleet Challenges with NVIDIA Vera CPUNVIDIA Developer
同一件事，来自我们关注的其他媒体。
这条新闻背后的模式
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。