English
Related papers

Related papers: COAT: Compressing Optimizer states and Activation …

200 papers

Structured State Space models (SSM) have recently emerged as a new class of deep learning models, particularly well-suited for processing long sequences. Their constant memory footprint, in contrast to the linearly scaling memory demands of…

Machine Learning · Computer Science 2025-07-09 Sebastian Siegel , Ming-Jay Yang , Younes Bouhadjar , Maxime Fabre , Emre Neftci , John Paul Strachan

The massive computational costs associated with large language model (LLM) pretraining have spurred great interest in reduced-precision floating-point representations to accelerate the process. As a result, the BrainFloat16 (BF16) precision…

Machine Learning · Computer Science 2025-03-26 Joonhyung Lee , Jeongin Bae , Byeongwook Kim , Se Jung Kwon , Dongsoo Lee

As the size of large language models grows exponentially, GPU memory has become a bottleneck for adapting these models to downstream tasks. In this paper, we aim to push the limits of memory-efficient training by minimizing memory usage on…

Machine Learning · Computer Science 2026-02-13 Sifeng Shang , Jiayi Zhou , Chenyu Lin , Minxian Li , Kaiyang Zhou

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing benchmarks. However, the escalating scale of model parameters imposes prohibitive memory overheads during training,…

Machine Learning · Computer Science 2026-04-28 Ziqing Wen , Ping Luo , Jiahuan Wang , Kun Yuan , Dongsheng Li , Tao Sun

Pretraining transformers are generally time-consuming. Fully quantized training (FQT) is a promising approach to speed up pretraining. However, most FQT methods adopt a quantize-compute-dequantize procedure, which often leads to suboptimal…

Machine Learning · Computer Science 2024-07-23 Haocheng Xi , Yuxiang Chen , Kang Zhao , Kai Jun Teh , Jianfei Chen , Jun Zhu

Federated learning (FL) is usually performed on resource-constrained edge devices, e.g., with limited memory for the computation. If the required memory to train a model exceeds this limit, the device will be excluded from the training.…

Machine Learning · Computer Science 2023-11-28 Kilian Pfeiffer , Ramin Khalili , Jörg Henkel

Fine-tuning models on edge devices like mobile phones would enable privacy-preserving personalization over sensitive data. However, edge training has historically been limited to relatively small models with simple architectures because…

Machine Learning · Computer Science 2022-07-19 Shishir G. Patil , Paras Jain , Prabal Dutta , Ion Stoica , Joseph E. Gonzalez

INT8 quantization has become one of the standard techniques for deploying convolutional neural networks (CNNs) on edge devices to reduce the memory and computational resource usages. By analyzing quantized performances of existing…

Machine Learning · Computer Science 2020-12-01 Taehoon Kim , YoungJoon Yoo , Jihoon Yang

One approach to reducing the massive costs of large language models (LLMs) is the use of quantized or sparse representations for training or deployment. While post-training compression methods are very popular, the question of obtaining…

Machine Learning · Computer Science 2025-06-12 Andrei Panferov , Jiale Chen , Soroush Tabesh , Roberto L. Castro , Mahdi Nikdan , Dan Alistarh

The transformer extends its success from the language to the vision domain. Because of the stacked self-attention and cross-attention blocks, the acceleration deployment of vision transformer on GPU hardware is challenging and also rarely…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Chong Yu , Tao Chen , Zhongxue Gan , Jiayuan Fan

Lately, post-training quantization methods have gained considerable attention, as they are simple to use, and require only a small unlabeled calibration set. This small dataset cannot be used to fine-tune the model without significant…

Machine Learning · Computer Science 2020-12-15 Itay Hubara , Yury Nahshan , Yair Hanani , Ron Banner , Daniel Soudry

Backpropagation has been the cornerstone of neural network training for decades, yet its inefficiencies in time and energy consumption limit its suitability for resource-constrained edge devices. While low-precision neural network…

Machine Learning · Computer Science 2025-07-01 Jingxiao Ma , Priyadarshini Panda , Sherief Reda

Quantization-aware training (QAT) is typically performed for a single target numeric format, while practical deployments often need to choose numerical precision at inference time based on hardware support or runtime constraints. We study…

Machine Learning · Computer Science 2026-04-02 Zifei Xu , Sayeh Sharify , Hesham Mostafa

Quantization is a key method for reducing the GPU memory requirement of training large language models (LLMs). Yet, current approaches are ineffective for 4-bit activations and 8-bit gradients, which would easily cause slow convergence or…

Computation and Language · Computer Science 2026-05-12 Wenxiang Lin , Juntao Huang , Luhan Zhang , Laili Li , Xiang Bao , Mengyang Zhang , Bing Wang , Shaohuai Shi

In this paper, we address the challenges posed by the substantial training time and memory consumption associated with video transformers, focusing on the ViViT (Video Vision Transformer) model, in particular the Factorised Encoder version,…

Computer Vision and Pattern Recognition · Computer Science 2023-06-09 Shreyank N Gowda , Anurag Arnab , Jonathan Huang

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

Corpus Aware Training (CAT) leverages valuable corpus metadata during training by injecting corpus information into each training example, and has been found effective in the literature, commonly known as the "tagging" approach. Models…

Machine Learning · Computer Science 2025-08-08 Yi-Hsiu Liao , Cheng Shen , Brenda , Yang

Edge applications, such as collaborative robotics and spacecraft rendezvous, demand efficient 6D object pose estimation on resource-constrained embedded platforms. Existing 6D pose estimation networks are often too large for such…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Saqib Javed , Chengkun Li , Andrew Price , Yinlin Hu , Mathieu Salzmann

Quantization is a technique for reducing deep neural networks (DNNs) training and inference times, which is crucial for training in resource constrained environments or applications where inference is time critical. State-of-the-art (SOTA)…

Machine Learning · Computer Science 2023-05-24 Lorenz Kummer , Kevin Sidak , Tabea Reichmann , Wilfried Gansterer

The growing use of large language models has raised environmental and economic concerns about their intensity of resource usage during inference. Serving these models to each user requires substantial energy and water for cooling. Model…

Machine Learning · Computer Science 2025-07-31 Deyu Cao , Samin Aref