English
Related papers

Related papers: Quantized Keys Steal Attention: Bias Correction fo…

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

While neural networks have advanced the frontiers in many applications, they often come at a high computational cost. Reducing the power and latency of neural network inference is key if we want to integrate modern networks into edge…

Machine Learning · Computer Science 2021-06-16 Markus Nagel , Marios Fournarakis , Rana Ali Amjad , Yelysei Bondarenko , Mart van Baalen , Tijmen Blankevoort

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

Neural network quantization is becoming an industry standard to efficiently deploy deep learning models on hardware platforms, such as CPU, GPU, TPU, and FPGAs. However, we observe that the conventional quantization approaches are…

Machine Learning · Computer Science 2019-04-19 Ji Lin , Chuang Gan , Song Han

Quantization is a promising method that reduces memory usage and computational intensity of Deep Neural Networks (DNNs), but it often leads to significant output error that hinder model deployment. In this paper, we propose Bias…

Computer Vision and Pattern Recognition · Computer Science 2024-06-26 Cheng Gong , Haoshuai Zheng , Mengting Hu , Zheng Lin , Deng-Ping Fan , Yuzhi Zhang , Tao Li

Quantization methods are widely used to accelerate inference and streamline the deployment of large language models (LLMs). Although quantization's effects on various LLM capabilities have been extensively studied, one critical area remains…

Computation and Language · Computer Science 2026-04-30 Qianli Wang , Mingyang Wang , Nils Feldhus , Simon Ostermann , Yuan Cao , Hinrich Schütze , Sebastian Möller , Vera Schmitt

Adversarial examples have emerged as a significant threat to machine learning algorithms, especially to the convolutional neural networks (CNNs). In this paper, we propose two quantization-based defense mechanisms, Constant Quantization…

Machine Learning · Computer Science 2020-05-15 Faiq Khalid , Hassan Ali , Hammad Tariq , Muhammad Abdullah Hanif , Semeen Rehman , Rehan Ahmed , Muhammad Shafique

The emergence of LLMs has ignited a fresh surge of breakthroughs in NLP applications, particularly in domains such as question-answering systems and text generation. As the need for longer context grows, a significant bottleneck in model…

Computation and Language · Computer Science 2024-04-15 Shichen Dong , Wen Cheng , Jiayu Qin , Wei Wang

Efficient attention algorithms are critical to mitigate the quadratic cost of attention in long-context workloads. Prior work utilises block-scaled quantisation techniques on Blackwell GPUs to move attention computation to 4-bit precision…

Machine Learning · Computer Science 2026-05-25 Joe Sharratt

The design of image and video quality assessment (QA) algorithms is extremely important to benchmark and calibrate user experience in modern visual systems. A major drawback of the state-of-the-art QA methods is their limited ability to…

Image and Video Processing · Electrical Eng. & Systems 2025-12-30 Shankhanil Mitra , Diptanu De , Shika Rao , Rajiv Soundararajan

Long-context inference is increasingly a memory-traffic problem. The culprit is the key--value (KV) cache: it grows with context length, batch size, layers, and heads, and it is read at every decoding step. Rotation-based scalar codecs meet…

Artificial Intelligence · Computer Science 2026-05-13 Namyoon Lee , Yongjune Kim

Deep learning for computer vision depends on lossy image compression: it reduces the storage required for training and test data and lowers transfer costs in deployment. Mainstream datasets and imaging pipelines all rely on standard JPEG…

Computer Vision and Pattern Recognition · Computer Science 2020-03-09 Zhijing Li , Christopher De Sa , Adrian Sampson

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

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

Recent advancements in reasoning language models have demonstrated remarkable performance in complex tasks, but their extended chain-of-thought reasoning process increases inference overhead. While quantization has been widely adopted to…

Computation and Language · Computer Science 2025-08-19 Ruikang Liu , Yuxuan Sun , Manyi Zhang , Haoli Bai , Xianzhi Yu , Tiezheng Yu , Chun Yuan , Lu Hou

Diffusion models have revolutionized image synthesis, setting new benchmarks in quality and creativity. However, their widespread adoption is hindered by the intensive computation required during the iterative denoising process.…

Computer Vision and Pattern Recognition · Computer Science 2024-09-19 Huanpeng Chu , Wei Wu , Chengjie Zang , Kun Yuan

Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintain performance. Existing methods use random linear hashing to…

Computation and Language · Computer Science 2025-10-10 Wenhao Li , Yuxin Zhang , Gen Luo , Haiyuan Wan , Ziyang Gong , Fei Chao , Rongrong Ji

Many computational factors limit broader deployment of large language models. In this paper, we focus on a memory bottleneck imposed by the key-value (KV) cache, a computational shortcut that requires storing previous KV pairs during…

Machine Learning · Computer Science 2024-06-13 Harry Dong , Xinyu Yang , Zhenyu Zhang , Zhangyang Wang , Yuejie Chi , Beidi Chen

Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models. Block diffusion improves inference efficiency via KV caching and block-wise causal inference and has been…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Zhuokun Chen , Jianfei Cai , Bohan Zhuang

Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents. However, existing diffusion-based methods are slow due to numerous denoising steps and costly…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Beijia Lu , Ziyi Chen , Jing Xiao , Jun-Yan Zhu
‹ Prev 1 4 5 6 7 8 10 Next ›