Towards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language Models
Hugging Face Blog1108 字 (约 5 分钟)
92
NVIDIA introduces Nemotron-Labs Diffusion, a diffusion-based language model family supporting AR, diffusion, and self-speculation modes, enabling parallel multi-token generation and iterative refinement for higher throughput and flexibility.
入选理由：Nemotron-Labs Diffusion 提供 3B/8B/14B 三档模型，支持商业友好许可证（NVIDIA Nemotron Open Model License）。
FeaturedArticle#Diffusion LM#NVIDIA#Nemotron#LLM Inference#Text Generation英文