# Speculative Decoding: Performance or Illusion?

arXiv: https://arxiv.org/abs/2601.11580 · HTML: https://mlsanity.com/paper/2601.11580/

## Key facts

- Cited by 15 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 23 of its 37 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [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)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [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)
- [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)
- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [Online Speculative Decoding](https://mlsanity.com/paper/2310.07177/) (2023)
- [Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding](https://mlsanity.com/paper/2402.12374/) (2024)
- [InstructCoder: Instruction Tuning Large Language Models for Code Editing](https://mlsanity.com/paper/2310.20329/) (2023)
- [PLD+: Accelerating LLM inference by leveraging Language Model Artifacts](https://mlsanity.com/paper/2412.01447/) (2024)
- [BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models](https://mlsanity.com/paper/2401.12522/) (2024)

## Built on by (most cited first, 15 of 15)

- [LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding](https://mlsanity.com/paper/2602.23881/) (2026)
- [ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios](https://mlsanity.com/paper/2604.09603/) (2026)
- [Multi-Token Prediction via Self-Distillation](https://mlsanity.com/paper/2602.06019/) (2026)
- [EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts](https://mlsanity.com/paper/2606.18967/) (2026)
- [D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding](https://mlsanity.com/paper/2607.14647/) (2026)
- [AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding](https://mlsanity.com/paper/2607.25852/) (2026)
- [A Practical Investigation of Training-free Relaxed Speculative Decoding](https://mlsanity.com/paper/2607.08690/) (2026)
- [Bole: Efficient Tree Speculation for Hybrid-Attention Language Models](https://mlsanity.com/paper/2608.01651/) (2026)
- [BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative Decoding](https://mlsanity.com/paper/2606.00144/) (2026)
- [K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling](https://mlsanity.com/paper/2606.10820/) (2026)
- [Adversarial Prompts for Acceptance Collapse in Speculative Decoding](https://mlsanity.com/paper/2607.21804/) (2026)
- [TreeSpark: Calibrated, Load-Adaptive Draft Trees for Semi-Autoregressive Speculative Decoding](https://mlsanity.com/paper/2609.22098/) (2026)
- [Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative Decoding](https://mlsanity.com/paper/2602.16994/) (2026)
- [AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines](https://mlsanity.com/paper/2610.01108/) (2026)
- [S3R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding](https://mlsanity.com/paper/2610.13202/) (2026)

## Abstract (arXiv)

Speculative decoding (SD) has become a popular technique to accelerate Large Language Model (LLM) inference, yet its real-world effectiveness remains unclear as prior evaluations rely on research prototypes and unrealistically small batch sizes. We present, to our knowledge, the first systematic study of SD on a production-grade and widely deployed inference engine (vLLM), covering multiple SD variants (n-gram, EAGLE/EAGLE-3, Draft-Model, Multi-Token Prediction) across diverse workloads, model scales, and batch sizes. We analyze key factors governing SD performance, and quantify a theoretical upper bound on SD speedup. Our results show that verification by the target model dominates the execution, while acceptance length varies markedly across output token positions, requests, and datasets. Comparing measured performance with theoretical bounds reveals substantial gaps between observed and theoretical upper bounds, and we leverage this observation to highlight new research opportunities that our study opens up in improving SD.