Skip to content
Preprint

Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting

Jul 2026 · 0 citations · 22 references
Computer Science

TL;DR

Progressive Tree Drafting (PTD) is proposed, which employs a structured, guided parallel drafting strategy to harness the model's parallel potential by coupling a progressive tree structure with a stepwise pruning mechanism and actively guides the LLM to explore multiple semantic paths in a single forward pass.

Abstract

Speculative decoding has significantly accelerated Large Language Model (LLM) inference by alleviating memory-bound bottlenecks. However, traditional speculative decoding typically relies on auxiliary draft modules, incurring significant training and communication overhead. Although recent methods attempt to generate drafts within the target model itself, they often fail to fully exploit its latent parallel capacity due to a lack of structural coordination. In this paper, we propose \textbf{Progressive Tree Drafting (PTD)}, which employs a structured, guided parallel drafting strategy to harness the model's parallel potential. By coupling a progressive tree structure with a stepwise pruning mechanism, PTD actively guides the LLM to explore multiple semantic paths in a single forward pass, ensuring both draft diversity and coherence. Experiments demonstrate that PTD achieves up to $2\times$ decoding speedup across various benchmarks while remaining training-free and model-agnostic. Our code is available at: https://github.com/MINE-USTC/PTD.

View source

Similar papers

Preprint Jul 2026

AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

AdaFlash framework is proposed, comprising two components: an on-policy distillation algorithm with reverse-KL divergence tailored for diffusion drafters, bringing stable convergence and effectively reducing domain-level variance and an adaptive length head that dynamically adjusts the candidate sequence length on the fly, substantially lowering the verification cost of the target model and handling token-level variance.

Yuanpan Qian, Hao Wu, Chen Chen et al. · 0 citations
Preprint Aug 2026

DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees

DARTree is introduced, a training-free speculative decoding method that extends a pretrained AR correction head from chains to trees, and achieves the highest average acceptance length and speedup in all four model--temperature configurations.

Tianyi Li, Yaxin Luo, Xinyi Shang et al. · 0 citations
Preprint Aug 2026

From Chains to Trees: Parent-Conditioned Drafting for Semi-Autoregressive Speculative Decoding

Speculative decoding accelerates LLM inference only when drafted continuations survive target-model verification. Semi-autoregressive drafters such as DSpark predict an entire token block with one backbone forward and refine it with a lightweight Markov head. However, DSpark decodes this block as a single chain, so an early mismatch invalidates the remaining suffix and limits the benefit of large draft blocks. We show that the conditional structure already learned by DSpark can support multiple parent-consistent continuations without retraining or additional backbone passes. We introduce Parent-Conditioned Drafting Tree (PCTree), which uses the pretrained Markov head to score alternative children separately for each concrete parent and allocates a fixed verification budget to the most probable paths. This converts DSpark's linear draft into a tree while preserving its one-pass parallel backbone. Across Qwen3-{4B,8B,14B} and nine benchmarks, at $B{=}7$, measured speedup gains over autoregressive (AR) decoding, relative to matched DSpark, range from $3.1\%$ to $29.5\%$. On Qwen3-4B GSM8K at $B{=}16$, PCTree increases mean acceptance length from $9.41$ to $11.16$ and three-run mean AR speedup from $6.14{\times}$ to $6.60{\times}$. These show that parent-conditioned branching can turn conditional capacity already present in a semi-autoregressive drafter into end-to-end inference gains through an inference-only change.

Zixian Li, Tong Li, C. Xie et al. · 1 citation
Preprint Jul 2026

AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding

DFly is proposed, a block-diffusion framework combining a hybrid target-conditioning backbone with a predecessor-conditioned autoregressive head, improving target-feature utilization and intra-block dependency modeling while keeping generation parallel, and DFly treats verification as a shared batch-level resource.

Hong Liu, Rui Cen, Junhan Shi et al. · 1 citation
Preprint Jul 2026

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding

A unified efficiency analysis is presented showing that extending the speculation horizon can reduce rather than improve speedup when the marginal acceptance probability falls below the relative drafting cost, and SparseSpec-L, a training-free self-speculative decoding framework for long-context inference is introduced.

Yue Liu, Yuan Zeng, Min Lyu et al. · 0 citations
Preprint Aug 2026

DBLAST: Dependent Block Drafting for Stochastic Speculative Decoding

This work proposes a dependent block drafter based on a low-rank latent mixture over token positions, complemented by an acceptance-oriented training objective that directly targets the expected verified length.

Amirmohammad Karimi, Chao Gao, Negar Hassanpour · 0 citations