English
Related papers

Related papers: RetrievalAttention: Accelerating Long-Context LLM …

200 papers

Large language models (LLMs) have been widely applied but face challenges in efficient inference. While quantization methods reduce computational demands, ultra-low bit quantization with arbitrary precision is hindered by limited GPU Tensor…

Machine Learning · Computer Science 2025-03-14 Shaobo Ma , Chao Fang , Haikuo Shao , Zhongfeng Wang

Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks. While these models have attained high accuracy by leveraging additional computation at test time, they need to generate long…

Computation and Language · Computer Science 2025-12-16 Coleman Hooper , Sebastian Zhao , Luca Manolache , Sehoon Kim , Michael W. Mahoney , Yakun Sophia Shao , Kurt Keutzer , Amir Gholami

Approximate Nearest Neighbor Search (ANNS) is a critical component of modern AI systems, such as recommendation engines and retrieval-augmented large language models (RAG-LLMs). However, scaling ANNS to billion-entry datasets exposes…

Hardware Architecture · Computer Science 2025-08-21 Sitian Chen , Amelie Chi Zhou , Yucheng Shi , Yusen Li , Xin Yao

Recent work has identified retrieval heads, a subset of attention heads responsible for retrieving salient information in long-context language models (LMs), as measured by their copy-paste behavior in Needlein-a-Haystack tasks. In this…

Computation and Language · Computer Science 2025-09-30 Wuwei Zhang , Fangcong Yin , Howard Yen , Danqi Chen , Xi Ye

Large language models (LLMs) predominantly employ decoder-only transformer architectures, necessitating the retention of keys/values information for historical tokens to provide contextual information and avoid redundant computation.…

Computation and Language · Computer Science 2024-06-04 Jianhui Pang , Fanghua Ye , Derek Fai Wong , Xin He , Wanshun Chen , Longyue Wang

The remarkable natural language understanding, reasoning, and generation capabilities of large language models (LLMs) have made them attractive for application to video understanding, utilizing video tokens as contextual input. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Jiaqi Xu , Cuiling Lan , Wenxuan Xie , Xuejin Chen , Yan Lu

Leveraging long contexts is crucial for advanced AI systems, but attention computation poses a scalability challenge. While scaled dot-product attention (SDPA) exhibits token sparsity, i.e. only a few pivotal tokens significantly contribute…

Machine Learning · Computer Science 2025-06-05 Aditya Desai , Shuo Yang , Alejandro Cuadron , Matei Zaharia , Joseph E. Gonzalez , Ion Stoica

Large language models (LLMs) are increasingly employed for complex tasks that process multiple generation calls in a tree structure with shared prefixes of tokens, including few-shot prompting, multi-step reasoning, speculative decoding,…

Computation and Language · Computer Science 2025-03-10 Jinwei Yao , Kaiqi Chen , Kexun Zhang , Jiaxuan You , Binhang Yuan , Zeke Wang , Tao Lin

Large language models (LLMs) have achieved impressive success, but their high memory requirements present challenges for long-context token generation. In this paper we study the streaming complexity of attention approximation, a key…

Machine Learning · Computer Science 2026-03-25 Ekaterina Kochetkova , Kshiteej Sheth , Insu Han , Amir Zandieh , Michael Kapralov

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine Learning · Computer Science 2025-07-01 Venmugil Elango

Long-context reasoning is a critical capability of large language models (LLMs), enabling applications such as long-document understanding, summarization, and code generation. However, efficient autoregressive inference relies on the…

Computation and Language · Computer Science 2026-04-28 Zahra Dehghanighobadi , Asja Fischer

Large Language Models (LLMs) require significant GPU memory when processing long texts, with the key value (KV) cache consuming up to 70\% of total memory during inference. Although existing compression methods reduce memory by evaluating…

Computation and Language · Computer Science 2025-10-15 Xiang Liu , Zhenheng Tang , Peijie Dong , Zeyu Li , Yue Liu , Bo Li , Xuming Hu , Xiaowen Chu

Retrieval-Augmented Language Modeling (RALM) by integrating large language models (LLM) with relevant documents from an external corpus is a proven method for enabling the LLM to generate information beyond the scope of its pre-training…

Computation and Language · Computer Science 2025-06-16 Runheng Liu , Xingchen Xiao , Heyan Huang , Zewen Chi , Zhijing Wu

While Key-Value (KV) cache succeeds in reducing redundant computations in auto-regressive models, it introduces significant memory overhead, limiting its practical deployment in long-sequence scenarios. Existing KV retrieval methods…

Machine Learning · Computer Science 2025-10-14 Wenbo Wu , Qingyi Si , Xiurui Pan , Ye Wang , Jie Zhang

Integrating vision models into large language models (LLMs) has sparked significant interest in creating vision-language foundation models, especially for video understanding. Recent methods often utilize memory banks to handle untrimmed…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Sakib Reza , Xiyun Song , Heather Yu , Zongfang Lin , Mohsen Moghaddam , Octavia Camps

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. These capabilities stem primarily from the self-attention mechanism, which enables modeling of long-range…

Computation and Language · Computer Science 2026-01-05 Zeng You , Yaofo Chen , Shuhai Zhang , Zhijie Qiu , Tingyu Wu , Yingjian Li , Yaowei Wang , Mingkui Tan

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 the computational needs of Large Vision-Language Models (LVLMs) increase, visual token pruning has proven effective in improving inference speed and memory efficiency. Traditional pruning methods in LVLMs predominantly focus on attention…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Bozhi Luan , Wengang Zhou , Hao Feng , Zhe Wang , Xiaosong Li , Houqiang Li

Efficient long-context inference is critical as large language models (LLMs) adopt context windows of ranging from 128K to 1M tokens. However, the growing key-value (KV) cache and the high computational complexity of attention create…

Computation and Language · Computer Science 2025-03-13 Guangtao Wang , Shubhangi Upasani , Chen Wu , Darshan Gandhi , Jonathan Li , Changran Hu , Bo Li , Urmish Thakker

The rapid growth of LLMs demands high-throughput, memory-capacity-intensive inference on resource-constrained edge devices, where single-batch decoding remains fundamentally memory-bound. Existing out-of-core GPU-based and SSD-like…

Hardware Architecture · Computer Science 2026-04-29 Mingbo Hao , Changwei Yan , Haoyu Cui , Zhihao Yan , Yizhi Ding , Zhangrui Qian , Weiwei Shan