English
Related papers

Related papers: Multi-matrix Factorization Attention

200 papers

Recent work has shown that attention-based language models excel at recall, the ability to ground generations in tokens previously seen in context. However, the efficiency of attention-based models is bottle-necked during inference by the…

Computation and Language · Computer Science 2025-03-10 Simran Arora , Sabri Eyuboglu , Michael Zhang , Aman Timalsina , Silas Alberti , Dylan Zinsley , James Zou , Atri Rudra , Christopher Ré

We introduce Kimi Linear, a hybrid linear attention architecture that, for the first time, outperforms full attention under fair comparisons across various scenarios -- including short-context, long-context, and reinforcement learning (RL)…

The Transformer-based Whisper model has achieved state-of-the-art performance in Automatic Speech Recognition (ASR). However, its Multi-Head Attention (MHA) mechanism results in significant GPU memory consumption due to the linearly growing…

Sound · Computer Science 2026-03-03 Sen Zhang , Jianguo Wei , Wenhuan Lu , Xianghu Yue , Wei Li , Qiang Li , Pengcheng Zhao , Ming Cai , Luo Si

The escalating context length in Large Language Models (LLMs) creates a severe performance bottleneck around the Key-Value (KV) cache, whose memory-bound nature leads to significant GPU under-utilization. This paper introduces Mixture of…

Machine Learning · Computer Science 2025-11-11 Myunghyun Rhee , Sookyung Choi , Euiseok Kim , Joonseop Sim , Youngpyo Joo , Hoshik Kim

KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or…

Machine Learning · Computer Science 2026-05-21 Dean Calver

Attention-based architectures have become ubiquitous in time series forecasting tasks, including spatio-temporal (STF) and long-term time series forecasting (LTSF). Yet, our understanding of the reasons for their effectiveness remains…

Machine Learning · Computer Science 2025-05-13 Suhan Guo , Jiahong Deng , Yi Wei , Hui Dou , Furao Shen , Jian Zhao

Chunked prefill has become a widely adopted serving strategy for long-context large language models, but efficient attention computation in this regime remains challenging. Existing sparse attention methods are primarily designed for…

Computation and Language · Computer Science 2026-05-19 Jiwon Song , Dongwon Jo , Beomseok Kang , Jae-Joon Kim

Computational workloads composing traditional transformer models are starkly bifurcated. Multi-Head Attention (MHA) and Grouped-Query Attention are memory-bound due to low arithmetic intensity, while FeedForward Networks are compute-bound.…

Large language model (LLM) inference demands significant amount of computation and memory, especially in the key attention mechanism. While techniques, such as quantization and acceleration algorithms, like FlashAttention, have improved…

Machine Learning · Computer Science 2024-12-18 Hao Kang , Srikant Bharadwaj , James Hensman , Tushar Krishna , Victor Ruhle , Saravan Rajmohan

Multi-Head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value states into a low-rank latent vector, caching only this vector to reduce memory. In tensor parallelism (TP), however, attention heads are computed across…

Machine Learning · Computer Science 2025-08-26 Xiaojuan Tang , Fanxu Meng , Pingzhi Tang , Yuxuan Wang , Di Yin , Xing Sun , Muhan Zhang

Efficient inference is critical for long-context language models, where attention computation and KV-cache access dominate the cost. Recent work RAT+, introduces a recurrence-augmented attention backbone that enables flexible dilated…

Machine Learning · Computer Science 2026-05-28 Xiuying Wei , Caglar Gulcehre

Motivated by the factorization inherent in the original fast multipole method and the improved fast Gauss transform we introduce a factorable form of attention that operates efficiently in high dimensions. This approach reduces the…

Machine Learning · Computer Science 2024-02-13 Armin Gerami , Monte Hoover , Pranav S. Dulepet , Ramani Duraiswami

Compressing the KV cache is a required step to deploy large language models on edge devices. Current quantization methods compress storage but fail to reduce bandwidth as attention calculation requires dequantizing keys from INT4/INT8 to…

Machine Learning · Computer Science 2026-01-16 Aryan Karmore

Long Chain-of-Thought (CoT) reasoning has significantly advanced the capabilities of Large Language Models (LLMs), but this progress is accompanied by substantial memory and latency overhead from the extensive Key-Value (KV) cache. Although…

Machine Learning · Computer Science 2025-12-23 Tao Zhang , Ziqian Zeng , Hao Peng , Huiping Zhuang , Cen Chen

Adapting Foundation Models to new domains with limited training data is challenging and computationally expensive. While prior work has demonstrated the effectiveness of using domain-specific exemplars as in-context demonstrations, we…

Artificial Intelligence · Computer Science 2025-10-08 Abhinav Jain , Xinyu Yao , Thomas Reps , Christopher Jermaine

As context windows in LLMs scale to 100K+ tokens, the key-value (KV) cache becomes the dominant memory bottleneck, with recent methods claiming 80-90% savings and minimal benchmark degradation. We argue these evaluations miss a structural…

Computation and Language · Computer Science 2026-03-03 Samhruth Ananthanarayanan , Ayan Sengupta , Tanmoy Chakraborty

Large Language Models (LLMs) have emerged as a pivotal research area, yet the attention module remains a critical bottleneck in LLM inference, even with techniques like KVCache to mitigate redundant computations. While various top-$k$…

While Transformer architecture excel at modeling long-range dependencies contributing to its widespread adoption in vision tasks the quadratic complexity of softmax-based attention mechanisms imposes a major bottleneck, particularly when…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yuan Cao , Dong Wang

The attention mechanism forms the foundational blocks for transformer language models. Recent approaches show that scaling the model achieves human-level performance. However, with increasing demands for scaling and constraints on hardware…

Computation and Language · Computer Science 2024-07-16 Sai Sena Chinnakonduru , Astarag Mohapatra

As large language models (LLMs) and visual language models (VLMs) grow in scale and application, attention mechanisms have become a central computational bottleneck due to their high memory and time complexity. While many efficient…

Machine Learning · Computer Science 2025-07-11 Zhengyu Tian , Anantha Padmanaban Krishna Kumar , Hemant Krishnakumar , Reza Rawassizadeh