English
Related papers

Related papers: Hurwitz Quaternion Multiplicative Quantization for…

200 papers

Large Language Model (LLM) inference is typically memory-intensive, especially when processing large batch sizes and long sequences, due to the large size of key-value (KV) cache. Vector Quantization (VQ) is recently adopted to alleviate…

Machine Learning · Computer Science 2025-12-16 Donghyun Son , Euntae Choi , Sungjoo Yoo

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

KV cache compression methods have mainly relied on scalar quantization techniques to reduce the memory requirements during decoding. In this work, we apply residual vector quantization, which has been widely used for high fidelity audio…

Machine Learning · Computer Science 2024-10-22 Ankur Kumar

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

Large language models (LLMs) have achieved outstanding performance across a wide range of natural language processing tasks, but their enormous parameter counts impose ubstantial memory and computational overheads. This challenge is…

Machine Learning · Computer Science 2026-04-07 Seoungsub Lee , In Seo Kim , Seon Wook Kim

Modern large language models (LLMs) drive interactive AI systems but are bottlenecked by the memory-heavy growth of key-value (KV) caches, which limits real-time throughput under concurrent loads. Existing KV-cache compression methods rely…

Machine Learning · Computer Science 2026-01-07 Joseph Kampeas , Emir Haleva

KV-cache quantization is framed as a quality--latency trade-off. We show it is \emph{inverted} on Apple Silicon's unified memory: a single fused Metal kernel (sign-randomized FFT $+$ per-channel $\lambda$ $+$ per-group abs-max $+$ int4…

Performance · Computer Science 2026-05-08 Mohamed Amine Bergach

We introduce QuaRot, a new Quantization scheme based on Rotations, which is able to quantize LLMs end-to-end, including all weights, activations, and KV cache in 4 bits. QuaRot rotates LLMs in a way that removes outliers from the hidden…

KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness. However, current methods have three unsolved issues:…

Machine Learning · Computer Science 2025-11-21 Xing Li , Zeyu Xing , Yiming Li , Linping Qu , Hui-Ling Zhen , Wulong Liu , Yiwu Yao , Sinno Jialin Pan , Mingxuan Yuan

Growing context lengths in transformer-based language models have made the key-value (KV) cache a critical inference bottleneck. While many KV cache pruning methods have been proposed, they have not yet been adopted in major inference…

Machine Learning · Computer Science 2026-02-04 Simon Jegou , Maximilian Jeblick

Continuous representation of words is a standard component in deep learning-based NLP models. However, representing a large vocabulary requires significant memory, which can cause problems, particularly on resource-constrained platforms.…

Computation and Language · Computer Science 2020-01-24 Siyu Liao , Jie Chen , Yanzhi Wang , Qinru Qiu , Bo Yuan

Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on…

Machine Learning · Computer Science 2024-02-21 Yuxuan Yue , Zhihang Yuan , Haojie Duanmu , Sifan Zhou , Jianlong Wu , Liqiang Nie

For the efficient inference of Large Language Models (LLMs), the effective compression of key-value (KV) cache is essential. Three main types of KV cache compression techniques, namely sparsity, channel compression, and quantization, have…

Machine Learning · Computer Science 2025-02-24 Hong Yankun , Li Xing , Zhen Hui-Ling , Yu Xianzhi , Liu Wulong , Yuan Mingxuan

Transformer-based large language models (LLMs) cache context as key-value (KV) pairs during inference. As context length grows, KV cache sizes expand, leading to substantial memory overhead and increased attention latency. This paper…

Databases · Computer Science 2025-10-01 Jang-Hyun Kim , Jinuk Kim , Sangwoo Kwon , Jae W. Lee , Sangdoo Yun , Hyun Oh Song

Compressing large language models (LLMs) for deployment on commodity GPUs remains challenging: conventional scalar quantization is limited to fixed bit-widths (e.g., 8/4/3-bit), offers only a few discrete compression points, and typically…

Machine Learning · Computer Science 2026-05-07 Ye Qiao , Yian Wang , Zhiheng Chen , Hyoukjun Kwon , Sitao Huang

The rapid scaling of Large Language Models (LLMs) elevates inference costs and compounds substantial deployment barriers. While quantization to 8 or 4 bits mitigates this, sub-3-bit methods face severe accuracy, scalability, and efficiency…

Quantization is an essential and popular technique for improving the accessibility of large language models (LLMs) by reducing memory usage and computational costs while maintaining performance. In this study, we apply 4-bit Group Scaling…

Computation and Language · Computer Science 2025-08-18 Sahil Sk , Debasish Dhal , Sonal Khosla , Sk Shahid , Sambit Shekhar , Akash Dhaka , Shantipriya Parida , Dilip K. Prasad , Ondřej Bojar

The key-value (KV) cache in large language models presents a significant memory bottleneck during inference, growing linearly with sequence length and often exceeding the memory footprint of model weights themselves. We implement and…

Machine Learning · Computer Science 2026-01-09 Maanas Taneja , Purab Shingvi

Large Language Models (LLMs) deliver strong performance but are difficult to deploy under tight memory and compute constraints. Low-bit post-training quantization (PTQ) is a promising direction; however, it typically relies on calibration…

Machine Learning · Computer Science 2026-02-09 Xinzhe Zheng , Zhen-Qun Yang , Zishan Liu , Haoran Xie , S. Joe Qin , Arlene Chen , Fangzhen Lin

Quantization is a widely-used compression technology to reduce the overhead of serving large language models (LLMs) on terminal devices and in cloud data centers. However, prevalent quantization methods, such as 8-bit weight-activation or…

Hardware Architecture · Computer Science 2024-10-17 Lian Liu , Haimeng Ren , Long Cheng , Zhaohui Xu , Yudong Pan , Mengdi Wang , Xiaowei Li , Yinhe Han , Ying Wang