English
Related papers

Related papers: Interleaved Head Attention

200 papers

Key-Value (KV) cache memory and bandwidth increasingly dominate large language model inference cost in long-context and long-generation regimes. Architectures such as multi-head latent attention (MLA) and hybrid sliding-window attention…

Computation and Language · Computer Science 2026-04-08 Zhen Cheng , Hao-Bo Yang , Wan-Yi Huang , Jin-Long Li

Scaling depth is a key driver for large language models (LLMs). Yet, as LLMs become deeper, they often suffer from signal degradation: informative features formed in shallow layers are gradually diluted by repeated residual updates, making…

Computation and Language · Computer Science 2026-03-17 Lianghui Zhu , Yuxin Fang , Bencheng Liao , Shijie Wang , Tianheng Cheng , Zilong Huang , Chen Chen , Lai Wei , Yutao Zeng , Ya Wang , Yi Lin , Yu Li , Xinggang Wang

Large Language Models (LLMs) have become the central paradigm in artificial intelligence, yet the core computational primitive of attention has remained structurally unchanged. Local Linear Attention (LLA) is an attention mechanism derived…

Machine Learning · Computer Science 2026-05-29 Yifei Zuo , Dhruv Pai , Zhichen Zeng , Alec Dewulf , Shuming Hu , Zhaoran Wang

We propose Hymba, a family of small language models featuring a hybrid-head parallel architecture that integrates transformer attention mechanisms with state space models (SSMs) for enhanced efficiency. Attention heads provide…

Transformer models rely on self-attention to capture token dependencies but face challenges in effectively integrating positional information while allowing multi-head attention (MHA) flexibility. Prior methods often model semantic and…

Machine Learning · Computer Science 2025-05-28 Jintian Shao , Hongyi Huang , Jiayi Wu , Beiwen Zhang , ZhiYu Wu , You Shan , MingKai Zheng

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Large Language Models (LLMs) struggle to perform such reasoning consistently. Here we propose an approach to pinpoint and rectify…

Computation and Language · Computer Science 2024-03-01 Mansi Sakarvadia , Aswathy Ajith , Arham Khan , Daniel Grzenda , Nathaniel Hudson , André Bauer , Kyle Chard , Ian Foster

Reducing the key-value (KV) cache size is a crucial step toward enabling efficient inference in large language models (LLMs), especially under latency and memory constraints. While Multi-Head Attention (MHA) offers strong representational…

Computation and Language · Computer Science 2025-09-23 Zhengge Cai , Haowen Hou

Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…

Computation and Language · Computer Science 2026-04-17 Zeng You , Yaofo Chen , Qiuwu Chen , Ying Sun , Shuhai Zhang , Yingjian Li , Yaowei Wang , Mingkui Tan

Transformers serve as the foundation of most modern large language models. To mitigate the quadratic complexity of standard full attention, various efficient attention mechanisms, such as linear and hybrid attention, have been developed. A…

Machine Learning · Computer Science 2026-02-03 Xiaowei Ye , Xiaoyu He , Chao Liao , Chen Wu , Pinyan Lu

Recent advances in large language models highlighted the excessive quadratic cost of self-attention. Despite the significant research efforts, subquadratic attention methods still suffer from inferior performance in practice. We hypothesize…

Machine Learning · Computer Science 2025-05-02 Piotr Piękos , Róbert Csordás , Jürgen Schmidhuber

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-06 Dimitrios Kafetzis , Ramin Khalili , Iordanis Koutsopoulos

We propose an efficient interactive method for multi-head self-attention via decomposition. For existing methods using multi-head self-attention, the attention operation of each head is computed independently. However, we show that the…

Computer Vision and Pattern Recognition · Computer Science 2024-02-28 Hankyul Kang , Ming-Hsuan Yang , Jongbin Ryu

The pursuit of reducing the memory footprint of the self-attention mechanism in multi-headed self attention (MHA) spawned a rich portfolio of methods, e.g., group-query attention (GQA) and multi-head latent attention (MLA). The methods…

Machine Learning · Computer Science 2026-04-01 Timon Klein , Jonas Kusch , Sebastian Sager , Stefan Schnake , Steffen Schotthöfer

More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Yanwen Fang , Yuxi Cai , Jintai Chen , Jingyu Zhao , Guangjian Tian , Guodong Li

Multi-headed Attention's (MHA) quadratic compute and linearly growing KV-cache make long-context transformers expensive to train and serve. Prior works such as Grouped Query Attention (GQA) and Multi-Latent Attention (MLA) shrink the cache,…

Computation and Language · Computer Science 2026-03-18 Tomas Figliolia , Nicholas Alonso , Rishi Iyer , Quentin Anthony , Beren Millidge

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

Multi-head latent attention (MLA) is designed to optimize KV cache memory through low-rank key-value joint compression. Rather than caching keys and values separately, MLA stores their compressed latent representations, reducing memory…

Computation and Language · Computer Science 2025-09-09 Guihong Li , Mehdi Rezagholizadeh , Mingyu Yang , Vikram Appia , Emad Barsoum

Key-value (KV) caching plays an essential role in accelerating decoding for transformer-based autoregressive large language models (LLMs). However, the amount of memory required to store the KV cache can become prohibitive at long sequence…

Machine Learning · Computer Science 2024-05-22 William Brandon , Mayank Mishra , Aniruddha Nrusimha , Rameswar Panda , Jonathan Ragan Kelly

Large language models (LLMs) have achieved impressive performance in numerous domains but often struggle to process lengthy inputs effectively and efficiently due to limited length generalization and attention's quadratic computational…

Computation and Language · Computer Science 2024-03-26 Yi Lu , Xin Zhou , Wei He , Jun Zhao , Tao Ji , Tao Gui , Qi Zhang , Xuanjing Huang

The quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts. Linear-time attention and State Space Models (SSMs) provide scalable alternatives but are typically…

Machine Learning · Computer Science 2026-05-15 Yifan Zhang , Zhen Qin , Mengdi Wang , Quanquan Gu