English
Related papers

Related papers: OSCAR: Offline Spectral Covariance-Aware Rotation …

200 papers

The self-attention mechanism is the key to the success of transformers in recent Large Language Models (LLMs). However, the quadratic computational cost $O(n^2)$ in the input sequence length $n$ is a notorious obstacle for further…

Machine Learning · Computer Science 2024-10-17 Yingyu Liang , Heshan Liu , Zhenmei Shi , Zhao Song , Zhuoyan Xu , Junze Yin

Quantization plays a crucial role in accelerating the inference of large-scale models, and rotational matrices have been shown to effectively improve quantization performance by smoothing outliers. However, end-to-end fine-tuning of…

Machine Learning · Computer Science 2025-11-07 Yuantian Shao , Yuanteng Chen , Peisong Wang , Jianlin Yu , Jing Lin , Yiwu Yao , Zhihui Wei , Jian Cheng

It is customary to deploy uniform scalar quantization in the end-to-end optimized Neural image compression methods, instead of more powerful vector quantization, due to the high complexity of the latter. Lattice vector quantization (LVQ),…

Image and Video Processing · Electrical Eng. & Systems 2024-11-26 Xi Zhang , Xiaolin Wu

Large Language Models (LLMs) have demonstrated remarkable capabilities. However, their massive parameter scale leads to significant resource consumption and latency during inference. Post-training weight-only quantization offers a promising…

Machine Learning · Computer Science 2026-05-12 Zhikai Li , Zhen Dong , Xuewen Liu , Jing Zhang , Qingyi Gu

As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-context LLM inference is challenging since the inference speed…

Computation and Language · Computer Science 2024-08-28 Jiaming Tang , Yilong Zhao , Kan Zhu , Guangxuan Xiao , Baris Kasikci , Song Han

Withtherapid advancement of large language models (LLMs), the context length for inference has been continuously increasing, leading to an exponential growth in the demand for Key-Value (KV) caching. This has resulted in a significant…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-11 Yanyu Liu , Jingying Fu , Sixiang Liu , Yitian Zou , You Fu , Jiehan Zhou , Shouhua Zhang

The transformer architecture predominates across various models. As the heart of the transformer, attention has a computational complexity of $O(N^2)$, compared to $O(N)$ for linear transformations. When handling large sequence lengths,…

Machine Learning · Computer Science 2025-10-02 Jintao Zhang , Jia Wei , Haofeng Huang , Pengle Zhang , Jun Zhu , Jianfei Chen

Reasoning models have demonstrated impressive performance in self-reflection and chain-of-thought reasoning. However, they often produce excessively long outputs, leading to prohibitively large key-value (KV) caches during inference. While…

This work studies how to adaptively recompute key-value (KV) caches for diffusion large language models (DLMs) to maximize prediction accuracy while minimizing decoding latency. Prior methods' decoders recompute QKV for all tokens at every…

Computation and Language · Computer Science 2025-12-30 Quan Nguyen-Tri , Mukul Ranjan , Zhiqiang Shen

Quantization-aware training (QAT) has achieved remarkable success in low-bit ($\leq$4-bit) quantization for classification networks. However, when applied to more complex visual tasks such as object detection and image segmentation,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Zhaoyang Wang , Dong Wang

Prefix KV caching has become a key mechanism in LLM serving: it reduces time to first token (TTFT) by avoiding redundant computation across requests that share a prefix (i.e., the system prompt). However, the accumulated KV cache is often…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-25 Yu Zhu , Aditya Dhakal , Yunming Xiao , Dejan Milojicic , Gustavo Alonso

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

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

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

As vision-language models (VLMs) tackle increasingly complex and multimodal tasks, the rapid growth of Key-Value (KV) cache imposes significant memory and computational bottlenecks during inference. While Multi-Head Latent Attention (MLA)…

Computer Vision and Pattern Recognition · Computer Science 2026-01-19 Xiaoran Fan , Zhichao Sun , Tao Ji , Lixing Shen , Tao Gui

Large generative models such as large language models (LLMs) and diffusion models have revolutionized the fields of NLP and computer vision respectively. However, their slow inference, high computation and memory requirement makes it…

Machine Learning · Computer Science 2024-03-29 Kartikeya Bhardwaj , Nilesh Prasad Pandey , Sweta Priyadarshi , Kyunggeun Lee , Jun Ma , Harris Teague

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance across diverse applications. However, their computational overhead during deployment remains a critical bottleneck. While Key-Value (KV) caching effectively…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Insu Han , Zeliang Zhang , Zhiyuan Wang , Yifan Zhu , Susan Liang , Jiani Liu , Haiting Lin , Mingjie Zhao , Chenliang Xu , Kun Wan , Wentian Zhao

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Computation and Language · Computer Science 2024-10-31 Suyu Ge , Yunan Zhang , Liyuan Liu , Minjia Zhang , Jiawei Han , Jianfeng Gao

KV-cache quantizers usually optimize storage-space reconstruction, even though attention reads keys through logits and values through attention-weighted readout. We argue that persistent cache error should be measured in model-visible…

Machine Learning · Computer Science 2026-05-21 Jorge L. Ruiz Williams

Large language models require massive memory footprints, severely limiting deployment on consumer hardware. Quantization reduces memory through lower numerical precision, but extreme 2-bit quantization suffers from catastrophic performance…

Machine Learning · Computer Science 2026-02-12 Bingxin Xu , Zhen Dong , Oussama Elachqar , Yuzhang Shang