Uno: Discrete Diffusion Delivers Lossless LLM Speedups

A new paper introduces Uno, which uses a lightweight diffusion adapter to draft tokens in parallel while the original autoregressive LLM verifies, achieving lossless 2.5x throughput gains on Qwen3-8B; authors also addressed overlap concerns with Orthrus.

2026-09-08 ~ 2026-09-09 · 4 related posts

Full story(2 episodes)→