English
Related papers

Related papers: Loki: Low-rank Keys for Efficient Sparse Attention

200 papers

Large Language Models (LLMs) are increasingly applied to data-intensive workflows, from database querying to developer observability. Yet the effectiveness of these systems is constrained by the volume, verbosity, and noise of real-world…

Software Engineering · Computer Science 2025-10-15 Marcus Emmanuel Barnes , Taher A. Ghaleb , Safwat Hassan

Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increases the computational cost. To address this problem, we…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Junyan Li , Delin Chen , Tianle Cai , Peihao Chen , Yining Hong , Zhenfang Chen , Yikang Shen , Chuang Gan

Long-Context Transformer Models (LCTMs) are vital for real-world applications but suffer high computational costs due to attention's quadratic complexity. Block-sparse attention mitigates this by focusing computation on critical regions,…

Computation and Language · Computer Science 2025-03-21 Ruyi Xu , Guangxuan Xiao , Haofeng Huang , Junxian Guo , Song Han

With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context generation. To compress the KV cache, recent methods…

Computation and Language · Computer Science 2025-10-28 Qingyue Yang , Jie Wang , Xing Li , Zhihai Wang , Chen Chen , Lei Chen , Xianzhi Yu , Wulong Liu , Jianye Hao , Mingxuan Yuan , Bin Li

The proliferation of long-context large language models (LLMs) exposes a key bottleneck: the rapidly expanding key-value cache during decoding, which imposes heavy memory and latency costs. While recent approaches attempt to alleviate this…

Computation and Language · Computer Science 2026-02-05 Gang Lin , Dongfang Li , Zhuoen Chen , Yukun Shi , Xuhui Chen , Baotian Hu , Min Zhang

Inference-time scaling trades efficiency for increased reasoning accuracy by generating longer or more parallel sequences. However, in Transformer LLMs, generation cost is bottlenecked by the size of the key-value (KV) cache, rather than…

Machine Learning · Computer Science 2025-11-10 Adrian Łańcucki , Konrad Staniszewski , Piotr Nawrot , Edoardo M. Ponti

Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up approach is to construct a smaller key-value (KV) cache,…

Computation and Language · Computer Science 2025-03-04 Fangyuan Xu , Tanya Goyal , Eunsol Choi

Large language models (LLMs) encounter computational challenges during long-sequence inference, especially in the attention pre-filling phase, where the complexity grows quadratically with the prompt length. Previous efforts to mitigate…

Machine Learning · Computer Science 2025-03-03 Xunhao Lai , Jianqiao Lu , Yao Luo , Yiyuan Ma , Xun Zhou

Large Language Models (LLMs) have been widely deployed in a variety of applications, and the context length is rapidly increasing to handle tasks such as long-document QA and complex logical reasoning. However, long context poses…

Machine Learning · Computer Science 2025-06-17 Guangda Liu , Chengwei Li , Jieru Zhao , Chenqi Zhang , Minyi Guo

Linear-attention models that compress the entire input sequence into a fixed-size recurrent state offer an efficient alternative to Transformers, but their finite memory induces forgetfulness that harms retrieval-intensive tasks. To…

Computation and Language · Computer Science 2025-10-27 Mutian He , Philip N. Garner

The deployment of large language models (LLMs) is often hindered by the extensive memory requirements of the Key-Value (KV) cache, especially as context lengths increase. Existing approaches to reduce the KV cache size involve either…

Computation and Language · Computer Science 2024-11-05 Alessio Devoto , Yu Zhao , Simone Scardapane , Pasquale Minervini

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

Block-wise diffusion language models (DLMs) generate multiple tokens in any order, offering a promising alternative to the autoregressive decoding pipeline. However, they still remain bottlenecked by memory-bound attention in long-context…

The Multi-Head Attention mechanism is central to LLM operation, and multiple works target its compute and memory efficiency during training. While most works focus on approximating the scaled dot product, the memory consumption of the…

Machine Learning · Computer Science 2026-03-03 Malik Khalaf , Yara Shamshoum , Nitzan Hodos , Yuval Sieradzki , Assaf Schuster

The rapid adoption of machine learning (ML) has underscored the importance of serving ML models with high throughput and resource efficiency. Traditional approaches to managing increasing query demands have predominantly focused on hardware…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-08 Sohaib Ahmad , Hui Guan , Ramesh K. Sitaraman

Large language models (LLMs) have demonstrated exceptional capabilities in generating text, images, and video content. However, as context length grows, the computational cost of attention increases quadratically with the number of tokens,…

Computation and Language · Computer Science 2025-04-23 Neusha Javidnia , Bita Darvish Rouhani , Farinaz Koushanfar

Dot-product attention has wide applications in computer vision and natural language processing. However, its memory and computational costs grow quadratically with the input size. Such growth prohibits its application on high-resolution…

Computer Vision and Pattern Recognition · Computer Science 2024-01-22 Zhuoran Shen , Mingyuan Zhang , Haiyu Zhao , Shuai Yi , Hongsheng Li

We revisit the I/O complexity of attention in large language models. Given query-key-value matrices $Q,K,V\in\mathbb{R}^{n\times d}$, and a machine with fast memory size $M$, the goal is to compute the "attention matrix" $A=\text{softmax}(Q…

Machine Learning · Computer Science 2026-05-25 Pál András Papp , Aleksandros Sobczyk , Anastasios Zouzias

Large language models (LLMs) have demonstrated remarkable performance, but their long-context reasoning remains constrained by the excessive memory required for the Key-Value (KV) cache. This makes KV cache compression a critical step…

Machine Learning · Computer Science 2025-09-30 Xianglong Yan , Zhiteng Li , Tianao Zhang , Haotong Qin , Linghe Kong , Yulun Zhang , Xiaokang Yang

As large language models (LLMs) continue to support increasingly longer contexts, the memory demand for key-value (KV) caches during decoding grows rapidly, becoming a critical bottleneck in both GPU memory capacity and PCIe bandwidth.…

Machine Learning · Computer Science 2025-06-23 Feiyu Yao , Qian Wang