English
Related papers

Related papers: FP4 All the Way: Fully Quantized Training of LLMs

200 papers

Training large-scale Mixture-of-Experts (MoE) models is bottlenecked by activation memory and expert-parallel communication, yet FP4 training remains impractical on Hopper-class GPUs without native MXFP4 or NVFP4 support. In this work, we…

Machine Learning · Computer Science 2026-03-04 Wuyue Zhang , Chongdong Huang , Chunbo You , Cheng Gu , Fengjuan Wang , Mou Sun

While neural networks have been remarkably successful in a wide array of applications, implementing them in resource-constrained hardware remains an area of intense research. By replacing the weights of a neural network with quantized…

Machine Learning · Computer Science 2023-01-18 Jinjie Zhang , Yixuan Zhou , Rayan Saab

Large language models (LLMs) have recently demonstrated remarkable performance across diverse language tasks. But their deployment is often constrained by their substantial computational and storage requirements. Quantization has emerged as…

Machine Learning · Computer Science 2024-10-24 Pranav Ajit Nair , Arun Sai Suggala

Post-Training Quantization (PTQ) converts pre-trained Full-Precision (FP) models into quantized versions without training. While existing methods reduce size and computational costs, they also significantly degrade performance and…

Machine Learning · Computer Science 2025-12-24 Boyang Zhang , Daning Cheng , Yunquan Zhang , Jiake Tian , Jing Li , Fangming Liu

Large language models (LLMs) have demonstrated remarkable capabilities in various kinds of tasks, while the billion or even trillion parameters bring storage and efficiency bottlenecks for inference. Quantization, particularly…

Machine Learning · Computer Science 2025-10-21 Mengtao Lv , Ruiqi Zhu , Xinyu Wang , Yun Li

Even though large language models are becoming increasingly capable, it is still unreasonable to expect them to excel at tasks that are under-represented on the Internet. Leveraging LLMs for specialized applications, particularly in niche…

Machine Learning · Computer Science 2025-08-18 Brendan R. Hogan , Will Brown , Adel Boyarsky , Anderson Schneider , Yuriy Nevmyvaka

Training LLMs at ultra-low precision remains a formidable challenge. Direct low-bit QAT often suffers from convergence instability and substantial training costs, exacerbated by quantization noise from heavy-tailed outlier channels and…

Machine Learning · Computer Science 2026-04-10 Binxing Xu , Hao Gu , Lujun Li , Hao Wang , Bei Liu , Jiacheng Liu , Qiyuan Zhu , Xintong Yang , Chao Li , Sirui Han , Yike Guo

FP8 is a natural progression for accelerating deep learning training inference beyond the 16-bit formats common in modern processors. In this paper we propose an 8-bit floating point (FP8) binary interchange format consisting of two…

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

Fine-tuning large language models (LLMs) is often constrained by the computational costs of processing massive datasets. We propose \textbf{QLESS} (Quantized Low-rank Gradient Similarity Search), which integrates gradient quantization with…

Large Language Models (LLMs) excel in diverse applications but suffer inefficiency due to massive scale. While quantization reduces computational costs, existing methods degrade accuracy in medium-sized LLMs (e.g., Llama-3-8B) due to…

Machine Learning · Computer Science 2025-03-26 Yuxuan Hu , Xiaodong Chen , Cuiping Li , Hong Chen , Jing Zhang

Large Language Models (LLMs) are proficient in natural language processing tasks, but their deployment is often restricted by extensive parameter sizes and computational demands. This paper focuses on post-training quantization (PTQ) in…

Computation and Language · Computer Science 2024-07-19 Janghwan Lee , Minsoo Kim , Seungcheol Baek , Seok Joong Hwang , Wonyong Sung , Jungwook Choi

Pre-training Transformers in FP4 precision is becoming a promising approach to gain substantial speedup, but it comes with a considerable loss of accuracy. Microscaling (MX) data format provides a fine-grained per-group quantization method…

Machine Learning · Computer Science 2025-07-10 Yuxiang Chen , Haocheng Xi , Jun Zhu , Jianfei Chen

The increasing size and complexity of large language models (LLMs) have raised significant challenges in deployment efficiency, particularly under resource constraints. Post-training quantization (PTQ) has emerged as a practical solution by…

Computation and Language · Computer Science 2026-04-07 Han Liu , Haotian Gao , Changya Li , Feng Zhang , Xiaotong Zhang , Wei Wang , Hong Yu

Large Language Models (LLMs) have attracted significant attention due to their human-like language understanding and generation capabilities, as well as their applicability across various domains. These models, characterized by their…

Machine Learning · Computer Science 2024-11-14 Kazuki Fujii , Taishi Nakamura , Rio Yokota

Model compression methods are used to reduce the computation and energy requirements for Large Language Models (LLMs). Quantization Aware Training (QAT), an effective model compression method, is proposed to reduce performance degradation…

Machine Learning · Computer Science 2024-10-16 He Li , Jianhang Hong , Yuanzhuo Wu , Snehal Adbol , Zonglin Li

Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization remains challenging. Existing methods, primarily based on…

Machine Learning · Computer Science 2025-05-29 Maosen Zhao , Pengtao Chen , Chong Yu , Yan Wen , Xudong Tan , Tao Chen

Large language models (LLMs) have revolutionized natural language processing, albeit at the cost of immense memory and computation requirements. Post-training quantization (PTQ) is becoming the de facto method to reduce the memory footprint…

Machine Learning · Computer Science 2024-10-28 Yuhang Li , Priyadarshini Panda

Quantizing the activation, weight, and gradient to 4-bit is promising to accelerate neural network training. However, existing 4-bit training methods require custom numerical formats which are not supported by contemporary hardware. In this…

Machine Learning · Computer Science 2023-06-26 Haocheng Xi , Changhao Li , Jianfei Chen , Jun Zhu

We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing…

Neural and Evolutionary Computing · Computer Science 2016-09-23 Itay Hubara , Matthieu Courbariaux , Daniel Soudry , Ran El-Yaniv , Yoshua Bengio
‹ Prev 1 8 9 10 Next ›