Uno speeds up Qwen3-8B 2.5x by using diffusion for parallel token drafting
rohanpaul_ai · x · 2026-09-09
Uno introduces a way to speed up existing LLMs without changing their output distribution: keep the original autoregressive model in charge of quality, and use lightweight diffusion adapters to draft multiple tokens in parallel, which the base model then verifies. This removes the need for a separate draft model and preserves the base model's sampling behavior.
- On Qwen3-8B, Uno delivered 2.5x higher per-request throughput and 1.6x higher system throughput at the largest tested batch size
- End-to-end RL training sped up by up to 40% in reported runs
Related event: Uno: Discrete Diffusion Delivers Lossless LLM Speedups(4 posts)→
More from Infra
- Dev submits PR adding periodic checkpoints to GKE sandboxes so agents don't lose progress — yoimnotkesku · 2026-11-19
- AWS Lambda Adds GPU Support via Managed Instances for Inference and Media Workloads — DavidWells · 2026-11-19
- Nvidia Allegedly Made GPUs Artificially Scarce to Keep Prices Sky-High — GaryMarcus · 2026-11-19
- Leak Hints at Classified 1M-GPU Training Cluster in China That Skips HBM — teortaxesTex · 2026-11-19
- Tencent leaned on Japanese neocloud for AI compute; DeepSeek, Zhipu best positioned — teortaxesTex · 2026-11-19
- Open-source prefill engine for GLM-5.3-Flash beats vLLM by 3.2x on 4x B200 — CShorten30 · 2026-11-19