paper-with-me

홈 › Papers

Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs

2024-05-24 · Chenxi Sun, Hongzhi Zhang, Zijia Lin, Jingyuan Zhang, Fuzheng Zhang, Zhongyuan Wang, Bin Chen, Chengru Song, Di Zhang, Kun Gai, Deyi Xiong

Large language models have demonstrated exceptional capability in natural language understanding and generation. However, their generation speed is limited by the inherently sequential nature of their decoding process, posing challenges for real-time applications. This paper introduces Lexical Unit Decoding (LUD), a novel decoding methodology implemented in a data-driven manner, accelerating the decoding process without sacrificing output quality. The core of our approach is the observation that a pre-trained language model can confidently predict multiple contiguous tokens, forming the basis for a \textit{lexical unit}, in which these contiguous tokens could be decoded in parallel. Extensive experiments validate that our method substantially reduces decoding time while maintaining generation quality, i.e., 33\% speed up on natural language generation with no quality loss, and 30\% speed up on code generation with a negligible quality loss of 3\%. Distinctively, LUD requires no auxiliary models and does not require changes to existing architectures. It can also be integrated with other decoding acceleration methods, thus achieving an even more pronounced inference efficiency boost. We posit that the foundational principles of LUD could define a new decoding paradigm for future language models, enhancing their applicability for a broader spectrum of applications. All codes are be publicly available at https://github.com/tjunlp-lab/Lexical-Unit-Decoding-LUD-. Keywords: Parallel Decoding, Lexical Unit Decoding, Large Language Model

📄 PDF Abstract BibTeX arXiv:2405.15208

Code (0)

등록된 구현이 없습니다.

Tasks

Code GenerationLanguage ModelingLanguage ModellingLarge Language ModelNatural Language UnderstandingText Generation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

2023-07-28 · Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang 외

This work aims at decreasing the end-to-end generation latency of large language models (LLMs). One of the major causes of the high generation latency is the sequential decoding approach adopted by almost all state-of-th…

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

2025-06-04 · Zhepei Wei, Wei-Lin Chen, Xinyu Zhu, Yu Meng

Large language models (LLMs) are increasingly used for long-content generation (e.g., long Chain-of-Thought reasoning) where decoding efficiency becomes a critical bottleneck: Autoregressive decoding is inherently limite…

Cerberus: Efficient Inference with Adaptive Parallel Decoding and Sequential Knowledge Enhancement

2024-10-17 · Yuxuan Liu, Wenyuan Li, Laizhong Cui, Hailiang Yang

Large language models (LLMs) often face a bottleneck in inference speed due to their reliance on auto-regressive decoding. Recently, parallel decoding has shown significant promise in enhancing inference efficiency. Howe…

Adaptive Skeleton Graph Decoding

2024-02-19 · Shuowei Jin, Yongji Wu, Haizhong Zheng, Qingzhao Zhang 외

Large language models (LLMs) have seen significant adoption for natural language tasks, owing their success to massive numbers of model parameters (e.g., 70B+); however, LLM inference incurs significant computation and m…

Lossless Acceleration for Seq2seq Generation with Aggressive Decoding

2022-05-20 · Tao Ge, Heming Xia, Xin Sun, Si-Qing Chen 외

We study lossless acceleration for seq2seq generation with a novel decoding algorithm -- Aggressive Decoding. Unlike the previous efforts (e.g., non-autoregressive decoding) speeding up seq2seq generation at the cost of …

Abstractive Text SummarizationGPUGrammatical Error CorrectionMachine Translation+3