# DFlash: Block Diffusion for Flash Speculative Decoding

arXiv: https://arxiv.org/abs/2602.06036 · HTML: https://mlsanity.com/paper/2602.06036/

## Key facts

- Cited by 135 papers in the map (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 27 of its 30 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)
- Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 27 of 27)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [Flex Attention: A Programming Model for Generating Optimized Attention Kernels](https://mlsanity.com/paper/2412.05496/) (2024)
- [Fast-dLLM v2: Efficient Block-Diffusion LLM](https://mlsanity.com/paper/2509.26328/) (2025)
- [SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation](https://mlsanity.com/paper/2510.06303/) (2025)
- [LongAlign: A Recipe for Long Context Alignment of Large Language Models](https://mlsanity.com/paper/2401.18058/) (2024)
- [MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding](https://mlsanity.com/paper/2408.11049/) (2024)
- [Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential](https://mlsanity.com/paper/2507.11851/) (2025)
- [DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding](https://mlsanity.com/paper/2510.02358/) (2025)
- [d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation](https://mlsanity.com/paper/2601.07568/) (2026)
- [SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding](https://mlsanity.com/paper/2511.00606/) (2025)

## Built on by (most cited first, 30 of 135)

- [Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding](https://mlsanity.com/paper/2605.29707/) (2026)
- [Accelerating Speculative Decoding with Block Diffusion Draft Trees](https://mlsanity.com/paper/2604.12989/) (2026)
- [DMax: Aggressive Parallel Decoding for dLLMs](https://mlsanity.com/paper/2604.08302/) (2026)
- [D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting](https://mlsanity.com/paper/2605.18810/) (2026)
- [Speculative Speculative Decoding](https://mlsanity.com/paper/2603.03251/) (2026)
- [JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting](https://mlsanity.com/paper/2606.18394/) (2026)
- [HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better](https://mlsanity.com/paper/2607.04884/) (2026)
- [Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?](https://mlsanity.com/paper/2602.23225/) (2026)
- [Draft-OPD: On-Policy Distillation for Speculative Draft Models](https://mlsanity.com/paper/2605.29343/) (2026)
- [Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM](https://mlsanity.com/paper/2604.06832/) (2026)
- [TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding](https://mlsanity.com/paper/2606.00487/) (2026)
- [DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding](https://mlsanity.com/paper/2606.02091/) (2026)
- [Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling](https://mlsanity.com/paper/2606.12370/) (2026)
- [Faster-WAM: Do World Action Models Need Deep Action Modules?](https://mlsanity.com/paper/2608.02365/) (2026)
- [PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding](https://mlsanity.com/paper/2605.08632/) (2026)
- [xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding](https://mlsanity.com/paper/2608.02438/) (2026)
- [Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding](https://mlsanity.com/paper/2605.20104/) (2026)
- [FLARE: Diffusion for Hybrid Language Model](https://mlsanity.com/paper/2606.01774/) (2026)
- [Cost-Aware Diffusion Draft Trees for Speculative Decoding](https://mlsanity.com/paper/2606.01813/) (2026)
- [DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees](https://mlsanity.com/paper/2608.13524/) (2026)
- [When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?](https://mlsanity.com/paper/2604.26412/) (2026)
- [D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding](https://mlsanity.com/paper/2607.14647/) (2026)
- [Verification-Aware Training for Speculative Decoding](https://mlsanity.com/paper/2608.30135/) (2026)
- [Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding](https://mlsanity.com/paper/2605.00342/) (2026)
- [Attention Drift: What Autoregressive Speculative Decoding Models Learn](https://mlsanity.com/paper/2605.09992/) (2026)
- [Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion](https://mlsanity.com/paper/2605.12825/) (2026)
- [TreeFlash: Parallel AR-Approximation for Faster Speculative Decoding](https://mlsanity.com/paper/2606.03819/) (2026)
- [DeLS-Spec: Decoupled Long-Short Contexts for Parallel Speculative Drafting](https://mlsanity.com/paper/2607.07409/) (2026)
- [AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding](https://mlsanity.com/paper/2607.25852/) (2026)
- [LiLiCorr: Lightweight Likelihood Correlation of Parallel Drafts for Speculative Decoding](https://mlsanity.com/paper/2608.20530/) (2026)

## Abstract (arXiv)

Autoregressive large language models (LLMs) deliver strong performance but require inherently sequential decoding, leading to high inference latency and poor GPU utilization. Speculative decoding mitigates this bottleneck by using a fast draft model whose outputs are verified in parallel by the target LLM; however, existing methods still rely on autoregressive drafting, which remains sequential and limits practical speedups. Diffusion LLMs offer a promising alternative by enabling parallel generation, but current diffusion models typically underperform compared with autoregressive models. In this paper, we introduce DFlash, a speculative decoding framework that employs a lightweight block diffusion model for parallel drafting. By generating draft tokens in a single forward pass and conditioning the draft model on context features extracted from the target model, DFlash enables efficient drafting with high-quality outputs and higher acceptance rates. Experiments show that DFlash achieves over 6x lossless acceleration across a range of models and tasks, delivering up to 2.5x higher speedup than the state-of-the-art speculative decoding method EAGLE-3.