English
Related papers

Related papers: DeFT: Decoding with Flash Tree-attention for Effic…

200 papers

The memory and computational demands of Key-Value (KV) cache present significant challenges for deploying long-context language models. Previous approaches attempt to mitigate this issue by selectively dropping tokens, which irreversibly…

Machine Learning · Computer Science 2024-07-24 Hanlin Tang , Yang Lin , Jing Lin , Qingsen Han , Shikuan Hong , Yiwu Yao , Gongyi Wang

Large language models (LLMs) have driven significant advancements across diverse NLP tasks, with long-context models gaining prominence for handling extended inputs. However, the expanding key-value (KV) cache size required by Transformer…

Machine Learning · Computer Science 2024-10-08 Lijie Yang , Zhihao Zhang , Zhuofu Chen , Zikun Li , Zhihao Jia

Optimizing inference for long-context large language models (LLMs) is increasingly important due to the quadratic compute and linear memory cost of Transformers. Existing approximate inference methods, including key-value (KV) cache…

Computation and Language · Computer Science 2026-02-03 Kevin Galim , Ethan Ewer , Wonjun Kang , Minjae Lee , Hyung Il Koo , Kangwook Lee

Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, the inference process involves two primary phases: prompt processing and token generation. Token generation, which…

Machine Learning · Computer Science 2024-04-09 Muhammad Adnan , Akhil Arunkumar , Gaurav Jain , Prashant J. Nair , Ilya Soloveychik , Purushotham Kamath

Recent large language models (LLMs) face increasing inference latency as input context length and model size continue to grow. In particular, the retrieval-augmented generation (RAG) technique, which enhances LLM responses by incorporating…

Artificial Intelligence · Computer Science 2025-04-17 Hyungwoo Lee , Kihyun Kim , Jinwoo Kim , Jungmin So , Myung-Hoon Cha , Hong-Yeon Kim , James J. Kim , Youngjae Kim

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA)…

Machine Learning · Computer Science 2026-04-10 Quantong Qiu , Zhiyi Hong , Yi Yang , Haitian Wang , Kebin Liu , Qingqing Dang , Juntao Li , Min Zhang

Large language models (LLMs) increasingly play an important role in a wide range of information processing and management tasks in industry. Many of these tasks are performed in large batches or even offline, and the performance indicator…

Computation and Language · Computer Science 2026-04-23 Zhen Zheng , Xin Ji , Taosong Fang , Fanghao Zhou , Chuanjie Liu , Gang Peng

Attention efficiency is critical to large language model (LLM) inference. While prior advances optimize attention execution for individual requests (e.g., FlashAttention), production LLM serving relies on batching requests with highly…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-09 Rui Ning , Wei Zhang , Fan Lai

Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with…

Hardware Architecture · Computer Science 2024-06-25 Hui Wu , Yi Gan , Feng Yuan , Jing Ma , Wei Zhu , Yutao Xu , Hong Zhu , Yuhua Zhu , Xiaoli Liu , Jinghui Gu , Peng Zhao

Long-context large language model (LLM) inference has become the norm for today's AI applications. However, it is severely bottlenecked by the increasing memory demands of its KV cache. Previous works have shown that self-speculative…

Machine Learning · Computer Science 2026-02-10 Yikang Yue , Yuqi Xue , Jian Huang

Efficient key-value (KV) cache management is crucial for the practical deployment of large language models (LLMs), yet existing compression techniques often incur a trade-off between performance degradation and computational overhead. We…

Machine Learning · Computer Science 2026-02-10 Jang-Hyun Kim , Dongyoon Han , Sangdoo Yun

PagedAttention is a popular approach for dynamic memory allocation in LLM serving systems. It enables on-demand allocation of GPU memory to mitigate KV cache fragmentation -- a phenomenon that crippled the batch size (and consequently…

Machine Learning · Computer Science 2025-01-30 Ramya Prabhu , Ajay Nayak , Jayashree Mohan , Ramachandran Ramjee , Ashish Panwar

Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire…

Computation and Language · Computer Science 2026-05-05 Hossein Entezari Zarch , Lei Gao , Chaoyi Jiang , Murali Annavaram

We demonstrate that geometrically distinctive keys during LLM inference tend to have high attention scores. Based on the phenomenon we propose KeyDiff, a training-free KV cache eviction method based solely on key similarity. Unlike other KV…

Artificial Intelligence · Computer Science 2026-01-21 Junyoung Park , Dalton Jones , Matthew J Morse , Raghavv Goel , Mingu Lee , Chris Lott

Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified…

Computation and Language · Computer Science 2025-02-06 You Wu , Haoyi Wu , Kewei Tu

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

Large language model (LLM) based agentic workflows have become a popular paradigm for coordinating multiple specialized agents to solve complex tasks. To improve serving efficiency, existing LLM systems employ prefix caching to reuse…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-11 Zaifeng Pan , Ajjkumar Patel , Zhengding Hu , Yipeng Shen , Yue Guan , Wan-Lu Li , Lianhui Qin , Yida Wang , Yufei Ding

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

Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators.…

Machine Learning · Computer Science 2025-04-11 Shaoyuan Chen , Wencong Xiao , Yutong Lin , Mingxing Zhang , Yingdi Shan , Jinlei Jiang , Kang Chen , Yongwei Wu

Generative reasoning with large language models (LLMs) often involves long decoding sequences, leading to substantial memory and latency overheads from accumulating key-value (KV) caches. While existing KV compression methods primarily…

Machine Learning · Computer Science 2025-12-16 Hui Zeng , Daming Zhao , Pengfei Yang , WenXuan Hou , Tianyang Zheng , Hui Li , Weiye Ji , Jidong Zhai