paper-with-me

Papers

SSSD: Simply-Scalable Speculative Decoding

2024-11-08 · Michele Marzollo, Jiawei Zhuang, Niklas Roemer, Lorenz K. Müller, Lukas Cavigelli

Over the past year, Speculative Decoding has gained popularity as a technique for accelerating Large Language Model inference. While several methods have been introduced, most struggle to deliver satisfactory performance at batch sizes typical for data centers ($\geq 8$) and often involve significant deployment complexities. In this work, we offer a theoretical explanation of how Speculative Decoding can be effectively utilized with larger batch sizes. We also introduce a method that integrates seamlessly into existing systems without additional training or the complexity of deploying a small LLM. In a continuous batching setting, we achieve a 4x increase in throughput without any latency impact for short context generation, and a 1.7-2x improvement in both latency and throughput for longer contexts.

📄 PDF Abstract BibTeX arXiv:2411.05894

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

2024-02-19 · Zhuoming Chen, Avner May, Ruslan Svirschevski, Yuhsun Huang 외

As the usage of large language models (LLMs) grows, performing efficient inference with these models becomes increasingly important. While speculative decoding has recently emerged as a promising direction for speeding u…

STree: Speculative Tree Decoding for Hybrid State-Space Models

2025-05-20 · Yangchao Wu, Zongyue Qin, Alex Wong, Stefano Soatto

Speculative decoding is a technique to leverage hardware concurrency to improve the efficiency of large-scale autoregressive (AR) Transformer models by enabling multiple steps of token generation in a single forward pass…

State Space Models

SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding

2026-03-19 · Shenggui Li, Chao Wang, Yikai Zhu, Yubo Wang 외 arxiv

Large language models incur high inference latency due to sequential autoregressive decoding. Speculative decoding alleviates this bottleneck by using a lightweight draft model to propose multiple tokens for batched veri…

RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding

2026-04-16 · Zihong Zhang, Zuchao Li, Lefei Zhang, Ping Wang 외 arxiv

Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-verify strategy, but existing training-fr…

DSD: A Distributed Speculative Decoding Solution for Edge-Cloud Agile Large Model Serving

2025-11-26 · Fengze Yu, Leshu Li, Brad McDanel, Sai Qian Zhang arxiv

Large language model (LLM) inference often suffers from high decoding latency and limited scalability across heterogeneous edge-cloud environments. Existing speculative decoding (SD) techniques accelerate token generatio…