This repository contains
Qwen3-4B-Thinking-Draft-OPD, a draft model for speculative decoding introduced in the paper
Draft-OPD: On-Policy Distillation for Speculative Draft Models.
Draft-OPD trains speculative draft models with on-policy target feedback. Instead of only learning from fixed target-generated trajectories, the drafter is supervised on draft-induced states exposed during speculative verification, including the positions where draft proposals are rejected.
Experiments show that Draft-OPD achieves over $5\times$ lossless acceleration for thinking models across diverse tasks, improving over EAGLE-3 and DFlash by 23% and 13%. For detailed training procedures, evaluation settings, and performance results, please refer to our paper:
https://arxiv.org/abs/2605.29343.
1@misc{lei2026draftopdonpolicydistillationspeculative,
2 title={Draft-OPD: On-Policy Distillation for Speculative Draft Models},
3 author={Haodi Lei and Yafy Li and Haoran Zhang and Shunkai Zhang and Qianjia Cheng and Xiaoye Qu and Ganqu Cui and Bowen Zhou and Ning Ding and Yun Luo and Yu Cheng},
4 year={2026},
5 eprint={2605.29343},
6 archivePrefix={arXiv},
7 primaryClass={cs.CL},
8 url={https://arxiv.org/abs/2605.29343},
9}
