# Accelerating Diffusion LLMs via Adaptive Parallel Decoding

arXiv: https://arxiv.org/abs/2506.00413 · HTML: https://mlsanity.com/paper/2506.00413/

## Key facts

- Cited by 112 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion LLM and MoE inference, one of 12 directions in Efficient LLM inference and serving.
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 31 May 2025.

## Placed in

- Efficient LLM inference and serving / [Diffusion LLM and MoE inference](https://mlsanity.com/inference/diffusion-llm-and-moe-inference/)

## Builds on (most cited first, 28 of 28)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data](https://mlsanity.com/paper/2406.03736/) (2024)
- [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://mlsanity.com/paper/2402.02057/) (2024)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions](https://mlsanity.com/paper/2502.06768/) (2025)
- [A Survey on Efficient Inference for Large Language Models](https://mlsanity.com/paper/2404.14294/) (2024)
- [Remasking Discrete Diffusion Models with Inference-Time Scaling](https://mlsanity.com/paper/2503.00307/) (2025)
- [Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion](https://mlsanity.com/paper/2408.05636/) (2024)
- [Discrete Copula Diffusion](https://mlsanity.com/paper/2410.01949/) (2024)
- [Semi-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1808.08583/) (2018)
- [Faster Cascades via Speculative Decoding](https://mlsanity.com/paper/2405.19261/) (2024)
- [Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding](https://mlsanity.com/paper/2504.20456/) (2025)
- [Parallel Sampling via Counting](https://mlsanity.com/paper/2408.09442/) (2024)
- [Enabling Autoregressive Models to Fill In Masked Tokens](https://mlsanity.com/paper/2502.06901/) (2025)
- [DynaMo: Accelerating Language Model Inference with Dynamic Multi-Token Sampling](https://mlsanity.com/paper/2405.00888/) (2024)

## Built on by (most cited first, 30 of 112)

- [Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing](https://mlsanity.com/paper/2508.09192/) (2025)
- [A Survey on Diffusion Language Models](https://mlsanity.com/paper/2508.10875/) (2025)
- [Diffusion Language Models Know the Answer Before Decoding](https://mlsanity.com/paper/2508.19982/) (2025)
- [dParallel: Learnable Parallel Decoding for dLLMs](https://mlsanity.com/paper/2509.26488/) (2025)
- [ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs](https://mlsanity.com/paper/2510.04767/) (2025)
- [TiDAR: Think in Diffusion, Talk in Autoregression](https://mlsanity.com/paper/2511.08923/) (2025)
- [Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language Models](https://mlsanity.com/paper/2508.00819/) (2025)
- [Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed](https://mlsanity.com/paper/2512.14067/) (2025)
- [AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Size](https://mlsanity.com/paper/2509.26432/) (2025)
- [A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models](https://mlsanity.com/paper/2508.08712/) (2025)
- [Learning Unmasking Policies for Diffusion Language Models](https://mlsanity.com/paper/2512.09106/) (2025)
- [LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning](https://mlsanity.com/paper/2510.04573/) (2025)
- [Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel Decoding](https://mlsanity.com/paper/2509.25188/) (2025)
- [Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding](https://mlsanity.com/paper/2607.05722/) (2026)
- [Set Block Decoding is a Language Model Inference Accelerator](https://mlsanity.com/paper/2509.04185/) (2025)
- [Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs](https://mlsanity.com/paper/2509.18085/) (2025)
- [Empirical Analysis of Decoding Biases in Masked Diffusion Models](https://mlsanity.com/paper/2508.13021/) (2025)
- [Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Models](https://mlsanity.com/paper/2510.00294/) (2025)
- [ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding](https://mlsanity.com/paper/2512.13586/) (2025)
- [DMax: Aggressive Parallel Decoding for dLLMs](https://mlsanity.com/paper/2604.08302/) (2026)
- [LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding](https://mlsanity.com/paper/2512.16229/) (2025)
- [Inpainting-Guided Policy Optimization for Diffusion Large Language Models](https://mlsanity.com/paper/2509.10396/) (2025)
- [A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation](https://mlsanity.com/paper/2510.19755/) (2025)
- [Unveiling the Potential of Diffusion Large Language Model in Controllable Generation](https://mlsanity.com/paper/2507.04504/) (2025)
- [DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs](https://mlsanity.com/paper/2603.12996/) (2026)
- [DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models](https://mlsanity.com/paper/2509.24296/) (2025)
- [Corrective Diffusion Language Models](https://mlsanity.com/paper/2512.15596/) (2025)
- [Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?](https://mlsanity.com/paper/2602.23225/) (2026)
- [Breaking the Factorization Barrier in Diffusion Language Models](https://mlsanity.com/paper/2603.00045/) (2026)
- [Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding](https://mlsanity.com/paper/2508.19529/) (2025)

## Abstract (arXiv)

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in practice struggle to achieve the speed of autoregressive models without significantly sacrificing quality. We therefore introduce adaptive parallel decoding (APD), a novel method that dynamically adjusts the number of tokens sampled in parallel. We achieve this by defining a multiplicative mixture between the dLLM marginal probabilities and the joint probability of sequences under a small auxiliary autoregressive model. This inverts the standard setup of speculative decoding, where the goal is to sample from a large autoregressive verifier by drafting from a smaller model. We further optimize APD by enabling KV caching and limiting the size of the masked input. Altogether, our method puts forward three tunable parameters to flexibly tradeoff throughput and quality. We show that APD provides markedly higher throughput with minimal quality degradations on downstream benchmarks.