English
Related papers

Related papers: Sherry: Hardware-Efficient 1.25-Bit Ternary Quanti…

200 papers

As large language models (LLMs) continue to grow in size and complexity, efficient checkpoint saving\&loading has become crucial for managing storage, memory usage, and fault tolerance in LLM training. The current works do not…

Machine Learning · Computer Science 2025-11-19 Yanxin Peng , Qingping Li , Baodong Wu , Shigang Li , Guohao Dai , Shengen Yan , Yu Wang

We propose a novel fine-grained quantization (FGQ) method to ternarize pre-trained full precision models, while also constraining activations to 8 and 4-bits. Using this method, we demonstrate a minimal loss in classification accuracy on…

Machine Learning · Computer Science 2017-05-31 Naveen Mellempudi , Abhisek Kundu , Dheevatsa Mudigere , Dipankar Das , Bharat Kaul , Pradeep Dubey

MobileNets family of computer vision neural networks have fueled tremendous progress in the design and organization of resource-efficient architectures in recent years. New applications with stringent real-time requirements on highly…

Machine Learning · Computer Science 2019-11-05 Dibakar Gope , Jesse Beu , Urmish Thakker , Matthew Mattina

Generative Large Language Models (LLMs) have demonstrated remarkable results for a wide range of tasks. However, deploying these models for inference has been a significant challenge due to their unprecedented resource requirements. This…

Computation and Language · Computer Science 2024-06-06 Sehoon Kim , Coleman Hooper , Amir Gholami , Zhen Dong , Xiuyu Li , Sheng Shen , Michael W. Mahoney , Kurt Keutzer

Deploying Large Language Models (LLMs) on resource-constrained edge devices like the Raspberry Pi presents challenges in computational efficiency, power consumption, and response latency. This paper explores quantization-based optimization…

Machine Learning · Computer Science 2025-04-04 Mahsa Ardakani , Jinendra Malekar , Ramtin Zand

Inference time, model size, and accuracy are three key factors in deep model compression. Most of the existing work addresses these three key factors separately as it is difficult to optimize them all at the same time. For example, low-bit…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Dan Liu , Xi Chen , Jie Fu , Chen Ma , Xue Liu

Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that…

Large language models (LLMs) have transformed artificial intelligence, but their computational requirements remain prohibitive for most users. Standard inference demands expensive datacenter GPUs or cloud API access, leaving over one…

Computation and Language · Computer Science 2026-05-08 Nii Osae Osae Dade , Tony Morri , Moinul Hossain Rahat , Sayandip Pal

Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weights, training these models still demands substantial memory…

Machine Learning · Computer Science 2025-10-13 Kaiyan Zhao , Tsuguchika Tabaru , Kenichi Kobayashi , Takumi Honda , Masafumi Yamazaki , Yoshimasa Tsuruoka

Ternary Neural Networks (TNNs) have received much attention due to being potentially orders of magnitude faster in inference, as well as more power efficient, than full-precision counterparts. However, 2 bits are required to encode the…

Machine Learning · Computer Science 2021-07-30 Peng Chen , Bohan Zhuang , Chunhua Shen

Neural network models are resource hungry. It is difficult to deploy such deep networks on devices with limited resources, like smart wearables, cellphones, drones, and autonomous vehicles. Low bit quantization such as binary and ternary…

Machine Learning · Computer Science 2021-09-15 Ryan Razani , Grégoire Morin , Vahid Partovi Nia , Eyyüb Sari

Binary quantization represents the most extreme form of compression, reducing weights to +/-1 for maximal memory and computational efficiency. While recent sparsity-aware binarization achieves sub-1-bit compression via weight pruning, it…

Machine Learning · Computer Science 2026-04-10 Hao Gu , Lujun Li , Hao Wang , Lei Wang , Zheyu Wang , Bei Liu , Jiacheng Liu , Qiyuan Zhu , Sirui Han , Yike Guo

We consider the problem of accurate sparse fine-tuning of large language models (LLMs), that is, fine-tuning pretrained LLMs on specialized tasks, while inducing sparsity in their weights. On the accuracy side, we observe that standard…

Computation and Language · Computer Science 2023-10-16 Eldar Kurtic , Denis Kuznedelev , Elias Frantar , Michael Goin , Dan Alistarh

Deploying Large Language Models (LLMs) on resource-constrained edge devices faces critical bottlenecks in memory bandwidth and power consumption. While ternary quantization (e.g., BitNet b1.58) significantly reduces model size, its direct…

Hardware Architecture · Computer Science 2026-05-05 Zi-Wei Lin , Tian-Sheuan Chang

We propose a cluster-based quantization method to convert pre-trained full precision weights into ternary weights with minimal impact on the accuracy. In addition, we also constrain the activations to 8-bits thus enabling sub 8-bit full…

Machine Learning · Computer Science 2017-02-02 Naveen Mellempudi , Abhisek Kundu , Dipankar Das , Dheevatsa Mudigere , Bharat Kaul

The benefits of most large language models come with steep and often hidden economic and environmental costs due to their resource usage inefficiency during deployment. Model quantization improves energy and memory efficiency through…

Machine Learning · Computer Science 2026-01-14 Deyu Cao , Yixin Yin , Samin Aref

Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-rank Adaptation…

Machine Learning · Computer Science 2026-01-29 Longteng Zhang , Sen Wu , Shuai Hou , Zhengyu Qing , Zhuo Zheng , Danning Ke , Qihong Lin , Qiang Wang , Shaohuai Shi , Xiaowen Chu

In this paper, we present the first structural binarization method for LLM compression to less than 1-bit precision. Although LLMs have achieved remarkable performance, their memory-bound nature during the inference stage hinders the…

Machine Learning · Computer Science 2024-10-10 Peijie Dong , Lujun Li , Yuedong Zhong , Dayou Du , Ruibo Fan , Yuhan Chen , Zhenheng Tang , Qiang Wang , Wei Xue , Yike Guo , Xiaowen Chu

Tensor parallelism provides an effective way to increase server large language model (LLM) inference efficiency despite adding an additional communication cost. However, as server LLMs continue to scale in size, they will need to be…

Artificial Intelligence · Computer Science 2024-11-13 Harry Dong , Tyler Johnson , Minsik Cho , Emad Soroush

Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or…

Computer Vision and Pattern Recognition · Computer Science 2018-07-03 Julian Faraone , Nicholas Fraser , Michaela Blott , Philip H. W. Leong