Official implementation of DDTree (Diffusion Draft Tree) from Accelerating Speculative Decoding with Block Diffusion Draft Trees.

Liran Ringel, Yaniv Romano

🌐 Project Page  |  📄 Paper

This codebase is intended for a CUDA-enabled PyTorch environment.

pip install -r requirements.txt

bash run_benchmark.sh

This produces benchmark outputs in runs/ and logs in logs/.

Generate the plots:

python3 plot_results.py

Generate the LaTeX table:

python3 make_latex_table.py

@article{ringel2026ddtree,
  title={Accelerating Speculative Decoding with Block Diffusion Draft Trees},
  author={Ringel, Liran and Romano, Yaniv},
  journal={arXiv preprint arXiv:2604.12989},
  year={2026}
}