sched-fast-diffusion-decoding

【效率与协作】Accelerate diffusion LLM decoding by halting when confidence stabilizes using progress-dependent thresholds. SchED achieves 3.8-4.0× speedup while retaining 99.8-100% quality—training-free and model-agnostic for any dLLM.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准