English
Related papers

Related papers: Max-Window Scale Estimation for Near-Lossless HiF8…

200 papers

Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency. We systematically investigate the interplay between quantization precision (FP16, INT8, INT4) and…

Machine Learning · Computer Science 2025-12-23 Michael S. Zhang , Rishi A. Ruia , Arnav Kewalram , Saathvik Dharmapuram , Utkarsh Sharma , Kevin Zhu

Reasoning models excel at complex tasks such as coding and mathematics, yet their inference is often slow and token-inefficient. To improve the inference efficiency, post-training quantization (PTQ) usually comes with the cost of large…

Machine Learning · Computer Science 2026-01-22 Keyu Lv , Manyi Zhang , Xiaobo Xia , Jingchen Ni , Shannan Yan , Xianzhi Yu , Lu Hou , Chun Yuan , Haoli Bai

This paper presents a comprehensive analysis of quantization techniques for optimizing Large Language Models (LLMs), specifically focusing on Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT). Through empirical…

Machine Learning · Computer Science 2024-11-12 Jahid Hasan

Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized model. The main bottleneck is its slow convergence and early performance plateau,…

In the era of large-scale language models, the substantial parameter size poses significant challenges for deployment. Being a prevalent compression technique, quantization has emerged as the mainstream practice to tackle this issue, which…

Computation and Language · Computer Science 2023-08-31 Qingyuan Li , Yifan Zhang , Liang Li , Peng Yao , Bo Zhang , Xiangxiang Chu , Yerui Sun , Li Du , Yuchen Xie

Large language models (LLMs) excel at natural language tasks but face deployment challenges due to their growing size outpacing GPU memory advancements. Model quantization mitigates this issue by lowering weight and activation precision,…

Computation and Language · Computer Science 2025-12-17 Shizhuo Mao , Song Chen , Yi Kang

Quantization-aware training (QAT) is an effective method to drastically reduce the memory footprint of LLMs while keeping performance degradation at an acceptable level. However, the optimal choice of quantization format and bit-width…

Machine Learning · Computer Science 2026-02-18 Sohir Maskey , Constantin Eichenberg , Johannes Messner , Douglas Orr

We introduce new methods for 1) accelerating and 2) stabilizing training for large language-vision models. 1) For acceleration, we introduce SwitchBack, a linear layer for int8 quantized training which provides a speed-up of 13-25% while…

Machine Learning · Computer Science 2023-10-18 Mitchell Wortsman , Tim Dettmers , Luke Zettlemoyer , Ari Morcos , Ali Farhadi , Ludwig Schmidt

In Large Language Models (LLMs), the number of parameters has grown exponentially in the past few years, e.g., from 1.5 billion parameters in GPT-2 to 175 billion in GPT-3 to possibly more than trillion in higher versions. This raises a…

Computation and Language · Computer Science 2026-01-06 Mahmoud Elgenedy

The deployment of Large Language Models (LLMs) on edge devices is fundamentally constrained by the "Memory Wall" -- a hardware limitation where memory bandwidth, not compute, becomes the bottleneck. Recent 1.58-bit quantization techniques…

Machine Learning · Computer Science 2026-02-06 David Alejandro Trejo Pizzo

When quantizing weights and activations to increasingly narrower representations, the cost of additions begins to dominate that of multiplications in multiply-accumulate (MAC) units. Recent studies show that reducing addition costs via…

Machine Learning · Computer Science 2025-08-01 Ian Colbert , Giuseppe Franco , Fabian Grob , Jinjie Zhang , Rayan Saab

We present a novel sub-8-bit quantization-aware training (S8BQAT) scheme for 8-bit neural network accelerators. Our method is inspired from Lloyd-Max compression theory with practical adaptations for a feasible computational overhead during…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-01 Kai Zhen , Hieu Duy Nguyen , Raviteja Chinta , Nathan Susanj , Athanasios Mouchtaris , Tariq Afzal , Ariya Rastrow

Quantization-aware training (QAT) is a common paradigm for network quantization, in which the training phase incorporates the simulation of the low-precision computation to optimize the quantization parameters in alignment with the task…

Machine Learning · Computer Science 2024-12-23 Chengting Yu , Shu Yang , Fengzhao Zhang , Hanzhi Ma , Aili Wang , Er-Ping Li

This paper presents the first study to explore the potential of parameter quantization for multimodal large language models to alleviate the significant resource constraint encountered during vision-language instruction tuning. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2024-08-08 Jingjing Xie , Yuxin Zhang , Mingbao Lin , Liujuan Cao , Rongrong Ji

Recent work has explored reduced numerical precision for parameters, activations, and gradients during neural network training as a way to reduce the computational cost of training (Na & Mukhopadhyay, 2016) (Courbariaux et al., 2014). We…

Machine Learning · Computer Science 2019-01-25 Ian Taras , Dylan Malone Stuart

We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We leverage weight normalization as a means of constraining parameters during…

Machine Learning · Computer Science 2023-02-01 Ian Colbert , Alessandro Pappalardo , Jakoba Petri-Koenig

Due to the high memory and computational costs associated with large language models (LLMs), model compression techniques such as quantization, which reduces inference costs, and parameter-efficient fine-tuning (PEFT) methods like Low-Rank…

Machine Learning · Computer Science 2025-07-23 Hyesung Jeon , Yulhwa Kim , Jae-joon Kim

Large language models (LLMs) require immense resources for training and inference. Quantization, a technique that reduces the precision of model parameters, offers a promising solution for improving LLM efficiency and sustainability. While…

Machine Learning · Computer Science 2025-02-18 Jacob Nielsen , Peter Schneider-Kamp , Lukas Galke

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

Deploying deep neural networks on resource-constrained 6G edge devices demands aggressive compression with minimal accuracy loss. Quantization-Aware Training (QAT) has emerged as a leading compression approach; however, existing…