deer-diffusion-speculative-decoding

【效率与协作】Enable efficient speculative decoding by training discrete diffusion language models for parallel draft generation. Use AR-style distillation and scribe refinement to train dLLMs. Eliminate left-to-right error accumulation through independent parallel proposals. Achieve 5.54× speedup on HumanEval vs. 2.41× for AR-based methods.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准