新闻
SGLang Adds Day-0 Support for NVIDIA Nemotron 3.5 Lightning
LMSYS · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- SGLang now supports NVIDIA Nemotron 3.5 Lightning, a 30-billion-parameter hybrid mixture-of-experts model with only 3 billion active parameters per token.
- 为何重要
- Engineers building agent systems, local assistants, or specialized enterprise workflows who need efficient inference with reasoning control and multi-token prediction.
- 注意
- DFlash requires a compatible draft checkpoint and pipeline parallel size 1. DSpark performs best on DGX Spark. Maximum throughput currently achieved without speculative decoding.
收听本摘要
- nemotron
这条新闻背后的模式
- Energy-Efficient Inference
- Hybrid Secret & Cache Management Pattern
- Local-Distant Agent Data Protection Pattern
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。