# Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion

arXiv: https://arxiv.org/abs/2408.05636 · HTML: https://mlsanity.com/paper/2408.05636/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Placed in Speculative decoding, one of 12 directions in Efficient LLM inference and serving.
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 10 Aug 2024.

## Placed in

- Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [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)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [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)
- [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)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions](https://mlsanity.com/paper/2102.05379/) (2021)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [Blockwise Parallel Decoding for Deep Autoregressive Models](https://mlsanity.com/paper/1811.03115/) (2018)
- [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://mlsanity.com/paper/2402.02057/) (2024)
- [Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding](https://mlsanity.com/paper/2401.07851/) (2024)
- [Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation](https://mlsanity.com/paper/2203.16487/) (2022)
- [Rolling Diffusion Models](https://mlsanity.com/paper/2402.09470/) (2024)
- [Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems](https://mlsanity.com/paper/2312.15234/) (2023)
- [The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs](https://mlsanity.com/paper/2210.14986/) (2022)
- [Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression](https://mlsanity.com/paper/2403.15447/) (2024)
- [SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices](https://mlsanity.com/paper/2406.02532/) (2024)
- [Recurrent Drafter for Fast Speculative Decoding in Large Language Models](https://mlsanity.com/paper/2403.09919/) (2024)

## Built on by (most cited first, 30 of 57)

- [Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking](https://mlsanity.com/paper/2505.24857/) (2025)
- [Accelerating Diffusion LLMs via Adaptive Parallel Decoding](https://mlsanity.com/paper/2506.00413/) (2025)
- [A Survey on Diffusion Language Models](https://mlsanity.com/paper/2508.10875/) (2025)
- [FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion](https://mlsanity.com/paper/2505.21467/) (2025)
- [Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment](https://mlsanity.com/paper/2501.19309/) (2025)
- [DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding](https://mlsanity.com/paper/2510.02358/) (2025)
- [Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices](https://mlsanity.com/paper/2410.11795/) (2024)
- [Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding](https://mlsanity.com/paper/2605.29707/) (2026)
- [Accelerated Diffusion Models via Speculative Sampling](https://mlsanity.com/paper/2501.05370/) (2025)
- [Self Speculative Decoding for Diffusion Large Language Models](https://mlsanity.com/paper/2510.04147/) (2025)
- [SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding](https://mlsanity.com/paper/2511.00606/) (2025)
- [DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference](https://mlsanity.com/paper/2601.19278/) (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)
- [CDLM: Consistency Diffusion Language Models For Faster Sampling](https://mlsanity.com/paper/2511.19269/) (2025)
- [Playing with Transformer at 30+ FPS via Next-Frame Diffusion](https://mlsanity.com/paper/2506.01380/) (2025)
- [Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Models](https://mlsanity.com/paper/2510.00294/) (2025)
- [Constrained Discrete Diffusion](https://mlsanity.com/paper/2503.09790/) (2025)
- [A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation](https://mlsanity.com/paper/2510.19755/) (2025)
- [Speculative Speculative Decoding](https://mlsanity.com/paper/2603.03251/) (2026)
- [dLLM: Simple Diffusion Language Modeling](https://mlsanity.com/paper/2602.22661/) (2026)
- [Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models](https://mlsanity.com/paper/2510.04146/) (2025)
- [Speeding up Speculative Decoding via Sequential Approximate Verification](https://mlsanity.com/paper/2502.04557/) (2025)
- [Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?](https://mlsanity.com/paper/2602.23225/) (2026)
- [DEER: Draft with Diffusion, Verify with Autoregressive Models](https://mlsanity.com/paper/2512.15176/) (2025)
- [DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding](https://mlsanity.com/paper/2606.02091/) (2026)
- [CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models](https://mlsanity.com/paper/2601.02236/) (2026)
- [PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding](https://mlsanity.com/paper/2605.08632/) (2026)
- [Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation](https://mlsanity.com/paper/2510.08994/) (2025)
- [DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees](https://mlsanity.com/paper/2608.13524/) (2026)

## Abstract (arXiv)

Speculative decoding has emerged as a widely adopted method to accelerate large language model inference without sacrificing the quality of the model outputs. While this technique has facilitated notable speed improvements by enabling parallel sequence verification, its efficiency remains inherently limited by the reliance on incremental token generation in existing draft models. To overcome this limitation, this paper proposes an adaptation of speculative decoding which uses discrete diffusion models to generate draft sequences. This allows parallelization of both the drafting and verification steps, providing significant speedups to the inference process. Our proposed approach, textitSpeculative Diffusion Decoding (SpecDiff), is validated on standard language generation benchmarks and empirically demonstrated to provide up to 7.2x speedups over standard generation processes and up to 1.75x speedups over existing speculative decoding approaches.