paper-with-me

Papers

Exploring and Improving Drafts in Blockwise Parallel Decoding

2024-04-14 · Taehyeon Kim, Ananda Theertha Suresh, Kishore Papineni, Michael Riley, Sanjiv Kumar, Adrian Benton

Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. as a method to improve inference speed of language models by simultaneously predicting multiple future tokens, termed block drafts, which are subsequently verified and conditionally accepted by the autoregressive model. This paper contributes to the understanding and improvement of block drafts in two ways. First, we analyze the token distributions produced by multiple prediction heads. Secondly, we leverage this analysis to develop algorithms to improve BPD inference speed by refining the block drafts using n-gram and neural language models. Experiments demonstrate that refined block drafts yield a +5-21% increase in block efficiency (i.e., the number of accepted tokens from the block draft) across diverse datasets.

📄 PDF Abstract BibTeX arXiv:2404.09221

Code (0)

등록된 구현이 없습니다.

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

Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding

2024-02-21 · Weilin Zhao, Yuxiang Huang, Xu Han, Wang Xu 외

Speculative decoding is a widely used method that accelerates the generation process of large language models (LLMs) with no compromise in model performance. It achieves this goal by using an existing smaller model for d…

Text Generation

PACER: Blockwise Pre-verification for Speculative Decoding with Adaptive Length

2026-02-01 · Situo Zhang, Yifan Zhang, Zichen Zhu, Hankun Wang 외 arxiv

Speculative decoding (SD) is a powerful technique for accelerating the inference process of large language models (LLMs) without sacrificing accuracy. Typically, SD employs a small draft model to generate a fixed number …

Blockwise Parallel Decoding for Deep Autoregressive Models

2018-11-07 · NeurIPS 2018 12 · Mitchell Stern, Noam Shazeer, Jakob Uszkoreit

Deep autoregressive sequence-to-sequence models have demonstrated impressive performance across a wide variety of tasks in recent years. While common architecture classes such as recurrent, convolutional, and self-attent…

DecoderImage Super-ResolutionMachine TranslationSuper-Resolution+1

DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation

2025-10-14 · Yakun Song, Xiaobin Zhuang, Jiawei Chen, Zhikang Niu 외 arxiv

Recent attempts to interleave autoregressive (AR) sketchers with diffusion-based refiners over continuous speech representations have shown promise, but they remain brittle under distribution shift and offer limited leve…

DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding

2025-09-28 · Guanghao Li, Zhihui Fu, Min Fang, Qibin Zhao 외 arxiv

As large language models (LLMs) scale up, accuracy improves, but the autoregressive (AR) nature of decoding increases latency since each token requires a serial forward pass. Speculative decoding addresses this by employ…