paper-with-me

홈 › Papers

HADES: Hardware Accelerated Decoding for Efficient Speculation in Large Language Models

2024-12-27 · Ze Yang, Yihong Jin, Xinhe Xu

Large Language Models (LLMs) have revolutionized natural language processing by understanding and generating human-like text. However, the increasing demand for more sophisticated LLMs presents significant computational challenges due to their scale and complexity. This paper introduces Hardware Accelerated Decoding (HADES), a novel approach to enhance the performance and energy efficiency of LLMs. We address the design of an LLM accelerator with hardware-level speculative decoding support, a concept not previously explored in existing literature. Our work demonstrates how speculative decoding can significantly improve the efficiency of LLM operations, paving the way for more advanced and practical applications of these models.

📄 PDF Abstract BibTeX arXiv:2412.19925

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Synergy of Speculative Decoding and Batching in Serving Large Language Models

2023-10-28 · Qidong Su, Christina Giannoula, Gennady Pekhimenko

Large Language Models (LLMs) like GPT are state-of-the-art text generation models that provide significant assistance in daily routines. However, LLM execution is inherently sequential, since they only produce one token …

GPUText Generation

Fast LLM Post-training via Decoupled and Fastest-of-N Speculation

2025-11-20 · Rongxin Cheng, Kai Zhou, Xingda Wei, Siyuan Liu 외 arxiv

Rollout dominates the training time in large language model (LLM) post-training, where the trained model is used to generate tokens given a batch of prompts. This work, SpecActor, achieves fast rollout with speculative d…

Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding

2025-12-29 · Yue Guan, Changming Yu, Shihan Fang, Weiming Hu 외 arxiv

Speculative decoding improves LLM inference by generating and verifying multiple tokens in parallel, but existing systems suffer from suboptimal performance due to a mismatch between dynamic speculation and static runtim…

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…

AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding

2025-01-21 · Zikun Li, Zhuofu Chen, Remi Delacourt, Gabriele Oliaro 외

Modern large language model (LLM) applications exhibit diverse service-level objectives (SLOs), from low-latency requirements in interactive coding assistants to more relaxed constraints in data wrangling tasks. Existing…

Language ModelingLanguage ModellingLarge Language ModelScheduling