Deer Diffusion Speculative Decoding

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.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit bdc2ccdb14

Frequently asked questions

npx get-skill add adu2021/deer-diffusion-speculative-decoding