# Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs arXiv: https://arxiv.org/abs/2512.20573 · HTML: https://mlsanity.com/paper/2512.20573/ ## Key facts - Cited by 4 papers in the map (data through 14 Oct 2026). - Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. - Builds on 36 of its 59 references that are in the map. - First posted on arXiv 23 Dec 2025. ## Placed in - LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/) - Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/) ## Builds on (most cited first, 30 of 36) - [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) - [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) - [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024) - [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025) - [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024) - [Dream 7B: Diffusion Large Language Models](https://mlsanity.com/paper/2508.15487/) (2025) - [Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding](https://mlsanity.com/paper/2505.22618/) (2025) - [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025) - [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025) - [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://mlsanity.com/paper/2402.02057/) (2024) - [Scaling Diffusion Language Models via Adaptation from Autoregressive Models](https://mlsanity.com/paper/2410.17891/) (2024) - [Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding](https://mlsanity.com/paper/2401.07851/) (2024) - [Mercury: Ultra-Fast Language Models Based on Diffusion](https://mlsanity.com/paper/2506.17298/) (2025) - [Deep Think with Confidence](https://mlsanity.com/paper/2508.15260/) (2025) - [An Empirical Study of Mamba-based Language Models](https://mlsanity.com/paper/2406.07887/) (2024) - [Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference](https://mlsanity.com/paper/2508.02193/) (2025) - [dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching](https://mlsanity.com/paper/2506.06295/) (2025) - [LLaDA2.0: Scaling Up Diffusion Language Models to 100B](https://mlsanity.com/paper/2512.15745/) (2025) - [REST: Retrieval-Based Speculative Decoding](https://mlsanity.com/paper/2311.08252/) (2023) - [dKV-Cache: The Cache for Diffusion Language Models](https://mlsanity.com/paper/2505.15781/) (2025) - [Fast-dLLM v2: Efficient Block-Diffusion LLM](https://mlsanity.com/paper/2509.26328/) (2025) - [Online Speculative Decoding](https://mlsanity.com/paper/2310.07177/) (2023) - [MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding](https://mlsanity.com/paper/2408.11049/) (2024) - [SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths](https://mlsanity.com/paper/2405.19715/) (2024) - [SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning](https://mlsanity.com/paper/2504.07891/) (2025) - [Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling](https://mlsanity.com/paper/2408.08696/) (2024) - [ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs](https://mlsanity.com/paper/2510.04767/) (2025) - [TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput](https://mlsanity.com/paper/2406.14066/) (2024) ## Built on by (most cited first, 4 of 4) - [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) - [AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters](https://mlsanity.com/paper/2607.19223/) (2026) - [Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative Decoding](https://mlsanity.com/paper/2602.16994/) (2026) ## Abstract (arXiv) Diffusion Large Language Models (dLLMs) offer fast, parallel token generation, but their standalone use is plagued by an inherent efficiency-quality tradeoff. We show that, if carefully applied, the attributes of dLLMs can actually be a strength for drafters in speculative decoding with autoregressive (AR) verifiers. Our core insight is that dLLM's speed from parallel decoding drastically lowers the risk of costly rejections, providing a practical mechanism to effectively realize the (elusive) lengthy drafts that lead to large speedups with speculative decoding. We present FailFast, a dLLM-based speculative decoding framework that realizes this approach by dynamically adapting its speculation length. It "fails fast" by spending minimal compute in hard-to-speculate regions to shrink speculation latency and "wins big" by aggressively extending draft lengths in easier regions to reduce verification latency (in many cases, speculating and accepting 70 tokens at a time!). Without any fine-tuning, FailFast delivers lossless acceleration of AR LLMs and achieves up to 4.9× speedup over vanilla decoding, 1.7× over the best naive dLLM drafter, and 1.7× over EAGLE-3 across diverse models and workloads. We open-source FailFast at https://github.com/ruipeterpan/failfast.