# DDTree — Diffusion Draft Trees for Faster Speculative Decoding

> Speculative decoding via diffusion draft trees — up to 8.22× speedup over autoregressive inference, beating EAGLE-3.

- Org: Technion
- Date: 2026-04-14
- Category: algorithm, repo, paper
- Source: https://github.com/liranringel/ddtree
- Canonical page: https://ai-tldr.dev/releases/liranringel-ddtree/

## In short

DDTree builds a multi-branch draft tree from a single block diffusion pass, then verifies the whole tree in one target-model forward pass. Achieves up to 8.22× speedup over autoregressive decoding and outperforms EAGLE-3 on math benchmarks.

## What it is

DDTree (Diffusion Draft Tree) accelerates LLM inference using speculative decoding. Instead of a single candidate token sequence per verification round, it builds a full tree of likely continuations from one block diffusion pass, then verifies the entire tree in a single forward pass of the target model. It is an extension of DFlash (block diffusion speculative decoding) that replaces its single-path drafting with tree-based drafting.

## How it works

The drafter (a small block diffusion model) produces per-position probability distributions over token sequences. DDTree selects branches to explore using a best-first heap algorithm under a fixed node budget, building a tree that maximizes the probability of finding accepted tokens. The target model verifies the full tree simultaneously using an ancestor-only attention mask. The method is lossless: the target model's output distribution is preserved exactly, so generation quality does not change.

## Why it matters

Getting more tokens per second from large models without changing their outputs is directly valuable for production inference costs. DDTree achieves 8.22× speedup on HumanEval with Qwen3-30B-MoE and outperforms EAGLE-3, a strong autoregressive drafter, on math benchmarks. The implementation is public and the benchmarks are reproducible.

## Who it's for

ML engineers optimizing LLM serving latency and throughput.

## Try it

git clone https://github.com/liranringel/ddtree && pip install -r requirements.txt && bash run_benchmark.sh

## Links

- [Repo](https://github.com/liranringel/ddtree)
- [Paper](https://arxiv.org/abs/2604.12989)
- [Project Page](https://liranringel.github.io/ddtree/)