English
Related papers

Related papers: InfLLM-V2: Dense-Sparse Switchable Attention for S…

200 papers

Transformer models have revolutionized natural language processing, achieving state-of-the-art performance and demonstrating remarkable scalability. However, their memory demands, particularly due to maintaining full context in memory, pose…

Computation and Language · Computer Science 2025-11-04 Juan Gabriel Kostelec , Qinghai Guo

As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging applications like LLM agents that highly depend on this…

Computation and Language · Computer Science 2026-04-09 Penghui Yang , Cunxiao Du , Fengzhuo Zhang , Haonan Wang , Tianyu Pang , Chao Du , Bo An

Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions. We turn this observation into VSA, a trainable, hardware-efficient…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Peiyuan Zhang , Yongqi Chen , Haofeng Huang , Will Lin , Zhengzhong Liu , Ion Stoica , Eric Xing , Hao Zhang

Large Language Models (LLMs) have exhibited exceptional performance across a spectrum of natural language processing tasks. However, their substantial sizes pose considerable challenges, particularly in computational demands and inference…

Computation and Language · Computer Science 2025-06-03 Guoxuan Chen , Han Shi , Jiawei Li , Yihang Gao , Xiaozhe Ren , Yimeng Chen , Xin Jiang , Zhenguo Li , Weiyang Liu , Chao Huang

Reasoning language models have demonstrated remarkable capabilities on challenging tasks by generating elaborate chain-of-thought (CoT) solutions. However, such lengthy generation shifts the inference bottleneck from compute-bound to…

We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-loss objective, we show on models up to 7B parameters that…

Machine Learning · Computer Science 2026-05-26 Florent Draye , Anson Lei , Hsiao-Ru Pan , Ingmar Posner , Bernhard Schölkopf

Extending the context length (i.e., the maximum supported sequence length) of LLMs is of paramount significance. To facilitate long context training of LLMs, sequence parallelism has emerged as an essential technique, which scatters each…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-12 Yujie Wang , Shiju Wang , Shenhan Zhu , Fangcheng Fu , Xinyi Liu , Xuefeng Xiao , Huixia Li , Jiashi Li , Faming Wu , Bin Cui

Vision-Language Models (vLLMs) have emerged as powerful architectures for joint reasoning over visual and textual inputs, enabling breakthroughs in image captioning, cross modal retrieval, and multimodal dialogue. However, as these models…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Andrew Kiruluta , Preethi Raju , Priscilla Burity

Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Xuan Zhang , Cunxiao Du , Sicheng Yu , Jiawei Wu , Fengzhuo Zhang , Wei Gao , Qian Liu

Attention-based sequence-to-sequence models have shown promising results in automatic speech recognition. Using these architectures, one-dimensional input and output sequences are related by an attention approach, thereby replacing more…

Computation and Language · Computer Science 2019-11-21 Parnia Bahar , Albert Zeyer , Ralf Schlüter , Hermann Ney

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

Speculative decoding is a powerful technique for reducing the latency of Large Language Models (LLMs), offering a fault-tolerant framework that enables the use of highly compressed draft models. In this work, we introduce Self-Distilled…

Computation and Language · Computer Science 2025-06-03 Mike Lasby , Nish Sinnadurai , Valavan Manohararajah , Sean Lie , Yani Ioannou , Vithursan Thangarasa

Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices…

Scaling Transformers to longer sequence lengths has been a major problem in the last several years, promising to improve performance in language modeling and high-resolution image understanding, as well as to unlock new applications in…

Machine Learning · Computer Science 2023-07-18 Tri Dao

Transformer-based large language models face severe scalability challenges in long-context generation due to the computational and memory costs of full-context attention. Under practical computation and memory constraints, many…

Computation and Language · Computer Science 2026-05-13 Xianpeng Shang , Jiang Li , Zehua Duo , Qianyi Cai , Xiangdong Su

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Computation and Language · Computer Science 2026-05-26 Spandan Pratyush

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Hardware Architecture · Computer Science 2025-01-15 Rya Sanovar , Srikant Bharadwaj , Renee St. Amant , Victor Rühle , Saravan Rajmohan

Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full…

Machine Learning · Computer Science 2025-02-19 Kan Zhu , Tian Tang , Qinyu Xu , Yile Gu , Zhichen Zeng , Rohan Kadekodi , Liangyu Zhao , Ang Li , Arvind Krishnamurthy , Baris Kasikci

To date, 2:4 sparsity has stood as the only sparse pattern that can be accelerated using sparse tensor cores on GPUs. In practice, 2:4 sparsity often possesses low actual speedups ($\leq 1.3$) and requires fixed sparse ratios, meaning that…

Machine Learning · Computer Science 2025-06-04 Kang Zhao , Tao Yuan , Han Bao , Zhenfeng Su , Chang Gao , Zhaofeng Sun , Zichen Liang , Liping Jing , Jianfei Chen

Long-context inference in Large Language Models (LLMs) is bottlenecked by the quadratic computation complexity of attention and the substantial memory footprint of Key-Value (KV) caches. While existing sparse attention mechanisms attempt to…

Computation and Language · Computer Science 2026-02-03 Xuan Ai , Qingqing Yang , Peng Wang , Lei Deng , Lin Zhang , Renhai Chen , Gong Zhang