paper-with-me

Papers

Speculative Decoding and Beyond: An In-Depth Review of Techniques

2025-02-27 · Yunhai Hu, Zining Liu, Zhenyuan Dong, Tianfan Peng, Bradley McDanel, Sai Qian Zhang

Sequential dependencies present a fundamental bottleneck in deploying large-scale autoregressive models, particularly for real-time applications. While traditional optimization approaches like pruning and quantization often compromise model quality, recent advances in generation-refinement frameworks demonstrate that this trade-off can be significantly mitigated. This survey presents a comprehensive taxonomy of generation-refinement frameworks, analyzing methods across autoregressive sequence tasks. We categorize methods based on their generation strategies (from simple n-gram prediction to sophisticated draft models) and refinement mechanisms (including single-pass verification and iterative approaches). Through systematic analysis of both algorithmic innovations and system-level implementations, we examine deployment strategies across computing environments and explore applications spanning text, images, and speech generation. This systematic examination of both theoretical frameworks and practical implementations provides a foundation for future research in efficient autoregressive decoding.

📄 PDF Abstract BibTeX arXiv:2502.19732

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Dynamic Depth Decoding: Faster Speculative Decoding for LLMs

2024-08-30 · Oscar Brown, Zhengjie Wang, Andrea Do, Nikhil Mathew 외

The acceleration of Large Language Models (LLMs) with speculative decoding provides a significant runtime improvement without any loss of accuracy. Currently, EAGLE-2 is the state-of-the-art speculative decoding method, …

Beyond the Speculative Game: A Survey of Speculative Execution in Large Language Models

2024-04-23 · Chen Zhang, Zhuorui Liu, Dawei Song

With the increasingly giant scales of (causal) large language models (LLMs), the inference efficiency comes as one of the core concerns along the improved performance. In contrast to the memory footprint, the latency bot…

Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding

2024-01-15 · Heming Xia, Zhe Yang, Qingxiu Dong, Peiyi Wang 외

To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this m…

Language ModelingLanguage ModellingLarge Language Model

Polybasic Speculative Decoding Through a Theoretical Perspective

2025-10-30 · Ruilin Wang, Huixia Li, Yuexiao Ma, Xiawu Zheng 외 arxiv

Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in accelerating inference without compromising the…

MoE-Spec: Expert Budgeting for Efficient Speculative Decoding

2026-02-17 · Bradley McDanel, Steven Li, Sruthikesh Surineni, Harshit Khaitan arxiv

Speculative decoding accelerates Large Language Model (LLM) inference by verifying multiple drafted tokens in parallel. However, for Mixture-of-Experts (MoE) models, this parallelism introduces a severe bottleneck: large…