# Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime Tradeoff

arXiv: https://arxiv.org/abs/2502.20704 · HTML: https://mlsanity.com/paper/2502.20704/

## Key facts

- Cited by 12 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 24 of its 28 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [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 Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [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)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification](https://mlsanity.com/paper/2305.09781/) (2023)
- [LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding](https://mlsanity.com/paper/2404.16710/) (2024)
- [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://mlsanity.com/paper/2402.02057/) (2024)
- [Speculative Decoding with Big Little Decoder](https://mlsanity.com/paper/2302.07863/) (2023)
- [Accelerating Transformer Inference for Translation via Parallel Decoding](https://mlsanity.com/paper/2305.10427/) (2023)
- [Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding](https://mlsanity.com/paper/2402.12374/) (2024)
- [PEARL: Parallel Speculative Decoding with Adaptive Draft Length](https://mlsanity.com/paper/2408.11850/) (2024)
- [GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding](https://mlsanity.com/paper/2402.02082/) (2024)
- [SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths](https://mlsanity.com/paper/2405.19715/) (2024)
- [Learning Harmonized Representations for Speculative Sampling](https://mlsanity.com/paper/2408.15766/) (2024)
- [Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment](https://mlsanity.com/paper/2501.19309/) (2025)
- [Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism](https://mlsanity.com/paper/2406.03853/) (2024)
- [Tandem Transformers for Inference Efficient LLMs](https://mlsanity.com/paper/2402.08644/) (2024)

## Built on by (most cited first, 12 of 12)

- [Accelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Execution](https://mlsanity.com/paper/2510.15312/) (2025)
- [See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs](https://mlsanity.com/paper/2604.05650/) (2026)
- [A Practical Investigation of Training-free Relaxed Speculative Decoding](https://mlsanity.com/paper/2607.08690/) (2026)
- [AdaSD: Adaptive Speculative Decoding for Efficient Language Model Inference](https://mlsanity.com/paper/2512.11280/) (2025)
- [Beyond the Target: From Imitation to Collaboration in Speculative Decoding](https://mlsanity.com/paper/2605.24793/) (2026)
- [When Is a Draft Accepted? A Theory of Acceptance in Speculative Decoding](https://mlsanity.com/paper/2606.30265/) (2026)
- [Approximate Speculative Decoding](https://mlsanity.com/paper/2608.03447/) (2026)
- [3-Model Speculative Decoding](https://mlsanity.com/paper/2510.12966/) (2025)
- [Faster LLM Inference via Sequential Monte Carlo](https://mlsanity.com/paper/2604.15672/) (2026)
- [Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes](https://mlsanity.com/paper/2607.26627/) (2026)
- [UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative Decoding](https://mlsanity.com/paper/2609.39972/) (2026)
- [Nucleus Speculative Decoding: Plausibility-Aware Verification Beyond Exact Distribution](https://mlsanity.com/paper/2610.07822/) (2026)

## Abstract (arXiv)

Speculative Decoding (SD) enforces strict distributional equivalence to the target model when accepting candidate tokens. While it maintains the target model's generation quality, this strict equivalence limits the speedup achievable by SD and prevents users from trading deviations from the target distribution in exchange for further inference speed gains. To address these limitations, we introduce Fuzzy Speculative Decoding (FSD) - a decoding algorithm that generalizes SD by accepting candidate tokens based on the divergences between the target and draft model distributions. By allowing for controlled divergence from the target model, FSD enables users to flexibly trade generation quality for inference speed. Across several benchmarks, our method is able to achieve significant runtime improvements of over 5 tokens per second faster than SD at only an approximate 2% absolute reduction in benchmark accuracy. In many cases, FSD is even able to match SD benchmark accuracy at over 2 tokens per second faster, demonstrating that distributional equivalence is not necessary to maintain target model performance. Furthermore, FSD can be seamlessly integrated into existing SD extensions; we demonstrate this by applying FSD to EAGLE-2, greatly enhancing this existing extension's efficiency while allowing it to leverage FSD's tunable quality-speed trade-off.