新闻
NVIDIA Vera Rubin NVL72 Leads Agentic Inference Performance on MLPerf Endpoints v1.0
NVIDIA Developer · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- NVIDIA Vera Rubin NVL72 achieves over 10x higher throughput per kilowatt than GB300 NVL72 on MLPerf Endpoints v1.0 agentic inference benchmarks.
- 为何重要
- Infrastructure engineers evaluating GPU platforms for multi-turn AI agent workloads with strict power and responsiveness constraints matter most.
- 注意
- Vera Rubin results are provisional and pending MLCommons verification. Comparisons use different GPU counts and concurrency levels across models.
- agent
- agentic
- reasoning
- inference
- serving
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。