English
Related papers

Related papers: RAP: KV-Cache Compression via RoPE-Aligned Pruning

200 papers

Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache…

Machine Learning · Computer Science 2025-09-22 Dmitry Akulov , Mohamed Sana , Antonio De Domenico , Tareq Si Salem , Nicola Piovesan , Fadhel Ayed

Real-world deployment of Vision-Language Models (VLMs) is hindered by high computational demands, as existing architectures inefficiently process all tokens uniformly. We introduce Adaptive Token Pruning (ATP), a dynamic inference mechanism…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Xue Li , Xiaonan Song , Henry Hu

Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key…

Computation and Language · Computer Science 2025-03-10 Giulio Corallo , Orion Weller , Fabio Petroni , Paolo Papotti

While Large Vision-Language Models (LVLMs) demonstrate exceptional multi-modal capabilities, the quadratic computational cost of processing high-resolution visual tokens remains a critical bottleneck. Though recent token reduction…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Surendra Pathak , Bo Han

Large Language Models (LLMs), such as LLaMA and T5, have shown exceptional performance across various tasks through fine-tuning. Although low-rank adaption (LoRA) has emerged to cheaply fine-tune these LLMs on downstream tasks, their…

Machine Learning · Computer Science 2024-08-08 Mingyang Zhang , Hao Chen , Chunhua Shen , Zhen Yang , Linlin Ou , Xinyi Yu , Bohan Zhuang

Rotary Positional Encoding (RoPE) is widely used in modern large language models. However, when sequences are extended beyond the range seen during training, rotary phases can enter out-of-distribution regimes, leading to spurious…

Machine Learning · Computer Science 2026-05-12 Riccardo Ali , Alessio Borgi , Christopher Irwin , Mario Severino , Pietro Liò

Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured pruning methods often employ a heuristic metric that…

Computation and Language · Computer Science 2026-01-28 Songtao Liu , Peng Liu

Reasoning LLMs (RLMs) such as OpenAI o1, DeepSeek-R1, and Qwen3 deliver strong multi-step reasoning through chain-of-thought generation, but their large model sizes and lengthy decode-time outputs make them costly to deploy and unsuitable…

Computation and Language · Computer Science 2025-12-03 Ziyan Wang , Enmao Diao , Qi Le , Pu Wang , Guanchu Wang , Minwoo Lee , Shu-ping Yeh , Li Yang

As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Existing approaches, such as KV quantization and pruning, reduce…

Machine Learning · Computer Science 2025-12-24 Tenghui Li , Guoxu Zhou , Xuyang Zhao , Yuning Qiu , Qibin Zhao

Extended reasoning in large language models (LLMs) creates severe KV cache memory bottlenecks. Leading KV cache compression methods estimate KV importance using attention scores from recent post-RoPE queries. However, queries rotate with…

Computation and Language · Computer Science 2026-04-07 Weian Mao , Xi Lin , Wei Huang , Yuxin Xie , Tianfu Fu , Bohan Zhuang , Song Han , Yukang Chen

Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications. However, their increased computational and memory demands present significant…

Computation and Language · Computer Science 2025-02-28 Yuhui Xu , Zhanming Jie , Hanze Dong , Lei Wang , Xudong Lu , Aojun Zhou , Amrita Saha , Caiming Xiong , Doyen Sahoo

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

Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT reasoning process imposes substantial memory overhead due to…

Computation and Language · Computer Science 2025-05-27 Tengxuan Liu , Shiyao Li , Jiayi Yang , Tianchen Zhao , Feng Zhou , Xiaohui Song , Guohao Dai , Shengen Yan , Huazhong Yang , Yu Wang

Recent reasoning-focused language models achieve high accuracy by generating lengthy intermediate reasoning paths before producing final answers. While this approach is effective in solving problems that require logical thinking, long…

Computation and Language · Computer Science 2025-10-27 Jiwon Song , Dongwon Jo , Yulhwa Kim , Jae-Joon Kim

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

A critical approach for efficiently deploying computationally demanding large language models (LLMs) is Key-Value (KV) caching. The KV cache stores key-value states of previously generated tokens, significantly reducing the need for…

Computation and Language · Computer Science 2024-09-10 Akide Liu , Jing Liu , Zizheng Pan , Yefei He , Gholamreza Haffari , Bohan Zhuang

Large Language Models (LLMs) face a significant bottleneck during autoregressive inference due to the massive memory footprint of the Key-Value (KV) cache. Existing compression techniques like token eviction, quantization, or other low-rank…

Machine Learning · Computer Science 2025-11-25 Santhosh G S , Saurav Prakash , Balaraman Ravindran

Large Language Models (LLMs), despite their remarkable performance across a wide range of tasks, necessitate substantial GPU memory and consume significant computational resources. Beyond the memory taken up by model weights, the memory…

Computation and Language · Computer Science 2024-06-24 Jincheng Dai , Zhuowei Huang , Haiyun Jiang , Chen Chen , Deng Cai , Wei Bi , Shuming Shi

Key-Value (KV) cache facilitates efficient large language models (LLMs) inference by avoiding recomputation of past KVs. As the batch size and context length increase, the oversized KV caches become a significant memory bottleneck,…

Machine Learning · Computer Science 2025-02-04 Zunhai Su , Zhe Chen , Wang Shen , Hanyu Wei , Linge Li , Huangqi Yu , Kehong Yuan

The recent advancements in large language models (LLMs) have significantly improved language understanding and generation capabilities. However, it is difficult to deploy LLMs on resource-constrained edge devices due to their high…

Computation and Language · Computer Science 2024-12-20 Haotian Zheng , Jinke Ren , Yushan Sun , Ruichen Zhang , Wenbo Zhang , Zhen Li , Dusit Niyato , Shuguang Cui , Yatong Han