English
Related papers

Related papers: DepCap: Adaptive Block-Wise Parallel Decoding for …

200 papers

Efficient parallelism is necessary for achieving low-latency, high-throughput inference with large language models (LLMs). Tensor parallelism (TP) is the state-of-the-art method for reducing LLM response latency, however GPU communications…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-27 Mert Hidayetoglu , Aurick Qiao , Michael Wyatt , Jeff Rasley , Yuxiong He , Samyam Rajbhandari

Diffusion LLMs (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs (AR-LLMs) with the potential to operate at significantly higher token generation rates. However, currently available open-source dLLMs often…

Machine Learning · Computer Science 2026-01-15 Sudhanshu Agrawal , Risheek Garrepalli , Raghavv Goel , Mingu Lee , Christopher Lott , Fatih Porikli

Diffusion Large Language Models (dLLMs) have demonstrated promising generative capabilities and are increasingly used to produce formal languages defined by context-free grammars, such as source code and chemical expressions. However, as…

Computation and Language · Computer Science 2026-02-10 Yitong Zhang , Yongmin Li , Yuetong Liu , Jia Li , Xiaoran Jia , Zherui Li , Ge Li

Speculative decoding is a powerful way to accelerate autoregressive large language models (LLMs), but directly porting it to vision-language models (VLMs) faces unique systems constraints: the prefill stage is dominated by visual tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Haiduo Huang , Fuwei Yang , Zhenhua Liu , Xuanwu Yin , Dong Li , Pengju Ren , Emad Barsoum

Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Euisoo Jung , Byunghyun Kim , Hyunjin Kim , Seonghye Cho , Jae-Gil Lee

Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging due to intractable sequence-level likelihoods. Existing…

Diffusion-based LLMs (dLLMs) fundamentally depart from traditional autoregressive (AR) LLM inference: they leverage bidirectional attention, block-wise KV cache refreshing, cross-step reuse, and a non-GEMM-centric sampling phase. These…

Hardware Architecture · Computer Science 2026-04-24 Binglei Lou , Haoran Wu , Kevin Lau , Gregor MacDonald , Jiayi Nie , Yao Lai , Can Xiao , Xuan Guo , Jianyi Cheng , Rika Antonova , Robert Mullins , Aaron Zhao

Speculative decoding is an effective and lossless method for Large Language Model (LLM) inference acceleration. It employs a smaller model to generate a draft token sequence, which is then verified by the original base model. In multi-GPU…

Machine Learning · Computer Science 2025-12-09 Yize Wu , Ke Gao , Ling Li , Yanjun Wu

To meet strict Service-Level Objectives (SLOs),contemporary Large Language Models (LLMs) decouple the prefill and decoding stages and place them on separate GPUs to mitigate the distinct bottlenecks inherent to each phase. However, the…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-10 Junhan Liao , Minxian Xu , Wanyi Zheng , Yan Wang , Kejiang Ye , Rajkumar Buyya , Chengzhong Xu

Diffusion-based language models (dLLMs) have emerged as a promising alternative to traditional autoregressive LLMs by enabling parallel token generation and significantly reducing inference latency. However, existing sampling strategies for…

Computation and Language · Computer Science 2026-04-01 Qingyan Wei , Yaojie Zhang , Zhiyuan Liu , Puyu Zeng , Yuxuan Wang , Biqing Qi , Dongrui Liu , Linfeng Zhang

Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR), motivated by their ability to use bidirectional context and adapt to a specific ASR…

Neural and Evolutionary Computing · Computer Science 2025-12-16 Dorian Koch , Albert Zeyer , Nick Rossenbach , Ralf Schlüter , Hermann Ney

Diffusion Large Language Models (dLLMs) have achieved rapid progress, viewed as a promising alternative to the autoregressive paradigm. However, most dLLM decoders still adopt a global confidence threshold, and do not explicitly model local…

Computation and Language · Computer Science 2026-04-09 Yuzhe Chen , Jiale Cao , Xuyang Liu , Jin Xie , Aiping Yang , Yanwei Pang

The limited understanding capacity of the visual encoder in Contrastive Language-Image Pre-training (CLIP) has become a key bottleneck for downstream performance. This capacity includes both Discriminative Ability (D-Ability), which…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Boyu Han , Qianqian Xu , Shilong Bao , Zhiyong Yang , Ruochen Cui , Xilin Zhao , Qingming Huang

Inference in diffusion large language models (dLLMs) is computationally expensive, as full self-attention must be repeatedly executed at each step of the denoising process without KV cache. Recent sparse attention methods for dLLMs mitigate…

Computation and Language · Computer Science 2026-05-21 Yanyi Lyu , Letian Chen , Futing Sun , Miao Zhang , Weili Guan , Liqiang Nie

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-attention networks make…

Machine Learning · Computer Science 2018-11-09 Mitchell Stern , Noam Shazeer , Jakob Uszkoreit

Discrete diffusion models are promising alternatives to autoregressive approaches for text generation, yet their decoding methods remain under-studied. Standard decoding methods for autoregressive models, such as beam search, do not…

Artificial Intelligence · Computer Science 2026-03-20 Jonathan Lys , Vincent Gripon , Bastien Pasdeloup , Axel Marmoret , Lukas Mauch , Fabien Cardinaux , Ghouthi Boukli Hacene

Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI, offering fully parallel token generation that can lead to significant throughput advantages and superior GPU utilization over the traditional…

Machine Learning · Computer Science 2026-05-15 Michael Rottoli , Subhankar Roy , Stefano Paraboschi

Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…

Sound · Computer Science 2026-01-27 Wenjie Tian , Bingshen Mu , Guobin Ma , Xuelong Geng , Zhixian Zhao , Lei Xie

Speculative decoding (SD) is a promising method for accelerating the decoding process of Large Language Models (LLMs). The efficiency of SD primarily hinges on the consistency between the draft model and the verify model. However, existing…

Computation and Language · Computer Science 2025-06-02 Longze Chen , Renke Shan , Huiming Wang , Lu Wang , Ziqiang Liu , Run Luo , Jiawei Wang , Hamid Alinejad-Rokny , Min Yang

Masked diffusion language models (MDLMs) offer the potential for parallel token generation, but most open-source MDLMs decode fewer than 5 tokens per model forward pass even with sophisticated sampling strategies, limiting their parallel…

Machine Learning · Computer Science 2026-02-09 Shirui Chen , Jiantao Jiao , Lillian J. Ratliff , Banghua Zhu