English
Related papers

Related papers: Tensor Cache: Eviction-conditioned Associative Mem…

200 papers

Token embeddings play a crucial role in language modeling but, despite this practical relevance, their theoretical understanding remains limited. Our paper addresses the gap by characterizing the structure of embeddings obtained via…

Machine Learning · Computer Science 2025-06-26 Diyuan Wu , Aleksandr Shevchenko , Samet Oymak , Marco Mondelli

Large Language Models (LLMs) use key-value (KV) cache to reduce redundant computation in autoregressive generation. However, the KV cache size increases linearly during generation, leading to excessive memory usage, especially for long…

Computation and Language · Computer Science 2025-03-04 Jian Yuan , Ziwei He , Haoli Bai , Jingwen Leng , Bo Jiang

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

Transformer-based language models have achieved remarkable performance across a wide range of tasks, yet their high inference latency poses a significant challenge for real-timeand large-scale deployment. While existing caching…

Computation and Language · Computer Science 2026-03-03 Harsh Vardhan Bansal

The rapid expansion of context window sizes in Large Language Models~(LLMs) has enabled them to tackle increasingly complex tasks involving lengthy documents. However, this progress comes at the cost of a substantial increase in memory…

Computation and Language · Computer Science 2025-08-05 Da Ma , Lu Chen , Situo Zhang , Yuxun Miao , Su Zhu , Zhi Chen , Hongshen Xu , Hanqi Li , Shuai Fan , Lei Pan , Kai Yu

Diffusion transformers have gained substantial interest in diffusion generative modeling due to their outstanding performance. However, their computational demands, particularly the quadratic complexity of attention mechanisms and…

Machine Learning · Computer Science 2026-01-28 Jinming Lou , Wenyang Luo , Yufan Liu , Bing Li , Xinmiao Ding , Weiming Hu , Yuming Li , Chenguang Ma

As the context length of current large language models (LLMs) rapidly increases, the memory demand for the Key-Value (KV) cache is becoming a bottleneck for LLM deployment and batch processing. Traditional KV cache compression methods…

Computation and Language · Computer Science 2025-12-23 Aomufei Yuan , Zhiming Wang , Ruijie Miao , Dayu Wang , Yuxuan Tian , Zihan Wang , Yebo Peng , Yuhan Wu , Bairen Yi , Xin Liu , Tong Yang

As large language models (LLMs) continue to advance, the demand for higher quality and faster processing of long contexts across various applications is growing. KV cache is widely adopted as it stores previously generated key and value…

Computation and Language · Computer Science 2025-02-28 Yingxin Li , Ye Li , Yuan Meng , Xinzhu Ma , Zihan Geng , Shutao Xia , Zhi Wang

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…

Computation and Language · Computer Science 2026-04-21 Zhiyuan Shi , Qibo Qiu , Feng Xue , Zhonglin Jiang , Li Yu , Jian Jiang , Xiaofei He , Wenxiao Wang

As the demand for processing extended textual data grows, the ability to handle long-range dependencies and maintain computational efficiency is more critical than ever. One of the key issues for long-sequence modeling using attention-based…

Computation and Language · Computer Science 2025-05-26 Aosong Feng , Rex Ying , Leandros Tassiulas

Long-context language models are limited by the memory footprint of the key-value (KV) cache. Existing training-free KV compression methods usually rank tokens by one importance signal -- attention, recency, layer-wise allocation, or key…

Computation and Language · Computer Science 2026-05-27 Hong Chen , Xiang Liu , Yubo Gao , Yuxuan Fan , Bo Wang , Yuanlin Chu , Yuanguo Lin , Xuming Hu

Transformer LLMs have been shown to exhibit strong reasoning ability that scales with inference-time compute, most prominently through token-space "thinking" chains of thought. A growing line of work pushes extra computation into the…

Machine Learning · Computer Science 2026-03-26 Adnan Oomerjee , Zafeirios Fountas , Haitham Bou-Ammar , Jun Wang

Key-value (KV) caching plays an essential role in accelerating decoding for transformer-based autoregressive large language models (LLMs). However, the amount of memory required to store the KV cache can become prohibitive at long sequence…

Machine Learning · Computer Science 2024-05-22 William Brandon , Mayank Mishra , Aniruddha Nrusimha , Rameswar Panda , Jonathan Ragan Kelly

In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of their key-value (KV) caches. Conventional cache management…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Zuyan Liu , Benlin Liu , Jiahui Wang , Yuhao Dong , Guangyi Chen , Yongming Rao , Ranjay Krishna , Jiwen Lu

A fundamental challenge in Visual Autoregressive models is the substantial memory overhead required during inference to store previously generated representations. Despite various attempts to mitigate this issue through compression…

Machine Learning · Computer Science 2026-01-26 Yang Cao , Xiaoyu Li , Yekun Ke , Yingyu Liang , Zhenmei Shi , Zhao Song

Sequence models face a fundamental tradeoff between memory capacity and computational efficiency. Transformers achieve expressive context modeling at quadratic cost, while linear attention and state-space models run in linear time by…

Machine Learning · Computer Science 2026-05-11 Yaxita Amin , Helen Zichen Li , Mengfan Zhang , Samet Ayhan

A method is presented for accelerating inference in transformer language models by exploiting the low effective rank of the token activation manifold at each layer. The method decomposes each activation vector into a subspace component and…

Machine Learning · Computer Science 2026-05-06 Stephen J. Thomas

The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint…

Machine Learning · Computer Science 2026-03-24 Yichun Xu , Navjot K. Khaira , Tejinder Singh

KV cache eviction has emerged as an effective solution to alleviate resource constraints faced by LLMs in long-context scenarios. However, existing token-level eviction methods often overlook two critical aspects: (1) their irreversible…

Machine Learning · Computer Science 2026-01-21 Yi Zhao , Yajuan Peng , Cam-Tu Nguyen , Zuchao Li , Xiaoliang Wang , Hai Zhao , Xiaoming Fu

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Computation and Language · Computer Science 2026-03-06 Jia-Nan Li , Jian Guan , Wei Wu , Chongxuan Li