English
Related papers

Related papers: SpecAttn: Speculating Sparse Attention

200 papers

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

Machine Learning · Computer Science 2020-10-27 Aurko Roy , Mohammad Saffar , Ashish Vaswani , David Grangier

Quantization is widely adopted to accelerate inference and reduce memory consumption in large language models (LLMs). While activation-weight joint quantization enables efficient low-precision decoding, it suffers from substantial…

Machine Learning · Computer Science 2025-10-03 Juntao Zhao , Wenhao Lu , Sheng Wang , Lingpeng Kong , Chuan Wu

Video large language models (Vid-LLMs) have shown strong capabilities in understanding video content. However, their reliance on dense video token representations introduces substantial memory and computational overhead in both prefilling…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Yicheng Ji , Jun Zhang , Heming Xia , Jinpeng Chen , Lidan Shou , Gang Chen , Huan Li

As the context window expands, self-attention increasingly dominates the transformer's inference time. Therefore, accelerating attention computation while minimizing performance degradation is essential for the efficient deployment of Large…

Computation and Language · Computer Science 2025-03-14 Eli Sason , Darya Frolova , Boris Nazarov , Felix Goldberd

Speculative decoding (SD), where a small draft model is employed to propose draft tokens in advance and then the target model validates them in parallel, has emerged as a promising technique for LLM inference acceleration. Many endeavors to…

Computation and Language · Computer Science 2026-04-30 Tianyu Liu , Qitan Lv , Hao Li , Xing Gao , Xiao Sun , Xiaoyan Sun

Recent advancements in Mixture of Experts (MoE) models have significantly increased their parameter scale as well as model performance. Extensive offloading techniques have been proposed to address the GPU memory limitations of MoE…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-03 Zhibin Wang , Zhonghui Zhang , Yuhang Zhou , Zibo Wang , Mo Zhou , Peng Jiang , Weilin Cai , Chengying Huan , Rong Gu , Sheng Zhong , Chen Tian

The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work…

Computation and Language · Computer Science 2025-10-16 Yang Li , Zhichen Dong , Yuhan Sun , Weixun Wang , Shaopan Xiong , Yijia Luo , Jiashun Liu , Han Lu , Jiamang Wang , Wenbo Su , Bo Zheng , Junchi Yan

The inference process for large language models is slow and memory-intensive, with one of the most critical bottlenecks being excessive Key-Value (KV) cache accesses. This paper introduces "Double Sparsity," a novel post-training sparse…

Machine Learning · Computer Science 2024-08-20 Shuo Yang , Ying Sheng , Joseph E. Gonzalez , Ion Stoica , Lianmin Zheng

This technical report describes the design and training of novel speculative decoding draft models, for accelerating the inference speeds of large language models in a production environment. By conditioning draft predictions on both…

Computation and Language · Computer Science 2024-06-10 Davis Wertheimer , Joshua Rosenkranz , Thomas Parnell , Sahil Suneja , Pavithra Ranganathan , Raghu Ganti , Mudhakar Srivatsa

Speculative decoding has emerged as a widely adopted method to accelerate large language model inference without sacrificing the quality of the model outputs. While this technique has facilitated notable speed improvements by enabling…

Computation and Language · Computer Science 2025-02-12 Jacob K Christopher , Brian R Bartoldson , Tal Ben-Nun , Michael Cardei , Bhavya Kailkhura , Ferdinando Fioretto

The growing demand for long-context inference capabilities in Large Language Models (LLMs) has intensified the computational and memory bottlenecks inherent to the self-attention mechanism. To address this challenge, we introduce BLASST, a…

The attention mechanism is the computational core of modern Transformer architectures, but its quadratic complexity in the input sequence length is the bottleneck for large-scale inference. This has motivated a rapidly growing body of work…

Transformer-based Large Language Models (LLMs) are the state-of-the-art for natural language tasks. Recent work has attempted to decode, by reverse engineering the role of linear layers, the internal mechanisms by which LLMs arrive at their…

Computation and Language · Computer Science 2023-10-26 Mansi Sakarvadia , Arham Khan , Aswathy Ajith , Daniel Grzenda , Nathaniel Hudson , André Bauer , Kyle Chard , Ian Foster

Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid…

Computation and Language · Computer Science 2026-05-29 Jaydip Sen , Subhasis Dasgupta , Hetvi Waghela

Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. However, the cascaded perception, reasoning, and tool-calling…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Haoyu Huang , Jinfa Huang , Zhongwei Wan , Xiawu Zheng , Rongrong Ji , Jiebo Luo

In modern large language models (LLMs), increasing the context length is crucial for improving comprehension and coherence in long-context, multi-modal, and retrieval-augmented language generation. While many recent transformer models…

Computation and Language · Computer Science 2025-01-24 Heejun Lee , Geon Park , Youngwan Lee , Jaduk Suh , Jina Kim , Wonyoung Jeong , Bumsik Kim , Hyemin Lee , Myeongjae Jeon , Sung Ju Hwang

Speculative decoding (SD) has been demonstrated as an effective technique for lossless LLM inference acceleration. Retrieval-based SD methods, one kind of model-free method, have yielded promising speedup, but they often rely on incomplete…

Computation and Language · Computer Science 2024-12-17 Yuxuan Hu , Ke Wang , Xiaokang Zhang , Fanjin Zhang , Cuiping Li , Hong Chen , Jing Zhang

Speculative decoding accelerates autoregressive inference by drafting candidate tokens with a fast model and verifying them in parallel with the target. Self-speculative methods avoid the need for an external drafter but have been studied…

Computation and Language · Computer Science 2026-05-05 Hector Borobia , Elies Seguí-Mas , Guillermina Tormo-Carbó

Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate tokens that are then verified in parallel by the target model. The speedup is significantly…

Machine Learning · Computer Science 2026-03-02 Alexander Samarin , Sergei Krutikov , Anton Shevtsov , Sergei Skvortsov , Filipp Fisin , Alexander Golubev

Speculative decoding (SD) has emerged as a method to accelerate LLM inference without sacrificing any accuracy over the 16-bit model inference. In a typical SD setup, the idea is to use a full-precision, small, fast model as "draft" to…

Computation and Language · Computer Science 2025-03-19 Evangelos Georganas , Dhiraj Kalamkar , Alexander Kozlov , Alexander Heinecke
‹ Prev 1 8 9 10 Next ›