lopa-lookahead

【效率与协作】Maximize parallelism in diffusion language models by intelligently exploring token filling orders. Spawn multiple candidate branches predicting high-confidence positions, evaluate all branches in one forward pass, and select the branch enabling most future parallelism—increasing tokens-per-forward-pass 4.4× without accuracy loss.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准