NVIDIA把30B模型劈成两半，并行写token，速度翻倍还保质量，不是新训模型是复用预训练，挺聪明的做法。
NVIDIA Research将30B参数的Nemotron-3-Nano-30B-A3B模型拆分为两半，一半维护上下文，一半生成token。该扩散语言模型仅复用预训练权重而非从头训练，在保持98.7%原始质量的同时实现了2.42倍的生成加速。这种方法将传统的自回归逐token生成改为并行写入，显著提升了推理效率。
We took a 30B model and split it in two to write tokens in parallel instead of one at a time. Intro...
We took a 30B model and split it in two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation. Your browser does not support the video tag. 🔗 View on Twitter 💬 16 🔄 29 ❤️ 227 👀 8296 📊 59 ⚡