Industry
Today’s LLMs still write like typewriters: one token at a time. This sequential process creates a hard inference bottleneck. We're introduci…
Today’s LLMs still write like typewriters: one token at a time. This sequential process creates a hard inference bottleneck. We're introducing Uno, a diffusion-augmented LLM that delivers autoregressi
Today’s LLMs still write like typewriters: one token at a time. This sequential process creates a hard inference bottleneck. We're introducing Uno, a diffusion-augmented LLM that delivers autoregressive quality at diffusion speed. It’s a lossless speedup method that accelerates generation without degrading response quality. With Uno, K2-Horizon-7B outperforms state-of-the-art diffusion methods in both quality and throughput, delivering up to a 2.2× speedup with no loss in quality. Paper: https://arxiv.org/abs/2609.04010 Model available at: https://huggingface.co/IFM/K2-Horizon-7B-Uno
Related
- Training a diffusion LLM from scratch is challenging, and diffusion inference advantages don't show up at training. So we convert instead. B…
- Introducing TokenSpeed, a speed-of-light LLM inference engine. > TensorRT LLM level performance > vLLM level usability > Built by a lean and…
- Train with autoregression & convert weights to diffusion for inference.
Source: Emad Mostaque (X) | 2026-09-17