# Mixture of Attentions For Speculative Decoding

arXiv: https://arxiv.org/abs/2410.03804 · HTML: https://mlsanity.com/paper/2410.03804/

## Key facts

- Cited by 17 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 32 of its 42 references that are in the map.
- First posted on arXiv 4 Oct 2024.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [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)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [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)
- [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)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [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)
- [DistillSpec: Improving Speculative Decoding via Knowledge Distillation](https://mlsanity.com/paper/2310.08461/) (2023)
- [REST: Retrieval-Based Speculative Decoding](https://mlsanity.com/paper/2311.08252/) (2023)
- [Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding](https://mlsanity.com/paper/2402.05109/) (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)
- [CLLMs: Consistency Large Language Models](https://mlsanity.com/paper/2403.00835/) (2024)
- [Aligning Large Language Models with Representation Editing: A Control Perspective](https://mlsanity.com/paper/2406.05954/) (2024)
- [Sparse Attention with Linear Units](https://mlsanity.com/paper/2104.07012/) (2021)
- [Nearest Neighbor Speculative Decoding for LLM Generation and Attribution](https://mlsanity.com/paper/2405.19325/) (2024)
- [Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters](https://mlsanity.com/paper/2406.16758/) (2024)

## Built on by (most cited first, 17 of 17)

- [Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening](https://mlsanity.com/paper/2601.21590/) (2026)
- [A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models](https://mlsanity.com/paper/2508.08712/) (2025)
- [Speculative Decoding and Beyond: An In-Depth Survey of Techniques](https://mlsanity.com/paper/2502.19732/) (2025)
- [On Almost Surely Safe Alignment of Large Language Models at Inference-Time](https://mlsanity.com/paper/2502.01208/) (2025)
- [VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMs](https://mlsanity.com/paper/2506.22694/) (2025)
- [Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding](https://mlsanity.com/paper/2503.10135/) (2025)
- [A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness](https://mlsanity.com/paper/2510.13890/) (2025)
- [P-EAGLE: Parallel-Drafting EAGLE with Scalable Training](https://mlsanity.com/paper/2602.01469/) (2026)
- [Towards Pervasive Distributed Agentic Generative AI -- A State of The Art](https://mlsanity.com/paper/2506.13324/) (2025)
- [Steering Pretrained Drafters during Speculative Decoding](https://mlsanity.com/paper/2511.09844/) (2025)
- [ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification](https://mlsanity.com/paper/2602.18447/) (2026)
- [The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus](https://mlsanity.com/paper/2603.20105/) (2026)
- [HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding](https://mlsanity.com/paper/2505.13254/) (2025)
- [TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification](https://mlsanity.com/paper/2601.23180/) (2026)
- [FASER: Fine-Grained Phase Management for Speculative Decoding in Dynamic LLM Serving](https://mlsanity.com/paper/2604.20503/) (2026)
- [Cross-Attention Speculative Decoding](https://mlsanity.com/paper/2505.24544/) (2025)
- [The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning](https://mlsanity.com/paper/2610.00332/) (2026)

## Abstract (arXiv)

The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy. Speculative decoding (SD) leverages smaller models to efficiently propose future tokens, which are then verified by the LLM in parallel. Small models that utilise activations from the LLM currently achieve the fastest decoding speeds. However, we identify several limitations of SD models including the lack of on-policyness during training and partial observability. To address these shortcomings, we propose a more grounded architecture for small models by introducing a Mixture of Attentions for SD. Our novel architecture can be applied in two scenarios: a conventional single device deployment and a novel client-server deployment where the small model is hosted on a consumer device and the LLM on a server. In a single-device scenario, we demonstrate state-of-the-art speedups improving EAGLE-2 by 9.5% and its acceptance length by 25%. In a client-server setting, our experiments demonstrate: 1) state-of-the-art latencies with minimal calls to the server for different network conditions, and 2) in the event of a complete disconnection, our approach can maintain higher accuracy compared to other SD methods and demonstrates advantages over API calls to LLMs, which would otherwise be unable to continue the generation process.