新闻
vLLM Support for NVIDIA Vera Rubin NVL72: 7.8x Throughput over GB200 NVL72
vLLM · vLLM Team, Inferact, Red Hat, and NVIDIA · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- vLLM now supports NVIDIA Vera Rubin NVL72 with optimized kernels, achieving 7.8x throughput gains over GB200 NVL72.
- 为何重要
- Matters for engineers deploying large language models at scale who need higher inference throughput and lower latency on latest NVIDIA hardware.
- 注意
- Performance results are early-stage; further optimization expected. Locality domain support still in active design and requires CUDA 13.4 with specific configuration modes.
- agent
- llm
- kernel
- throughput
- vllm
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。