English
Related papers

Related papers: Accurate INT8 Training Through Dynamic Block-Level…

200 papers

Quantization is a powerful tool for accelerating large language model (LLM) inference, but the accuracy-performance trade-offs across different formats remain unclear. In this paper, we conduct the most comprehensive empirical study to…

Machine Learning · Computer Science 2026-05-27 Eldar Kurtic , Alexandre Marques , Shubhra Pandit , Mark Kurtz , Dan Alistarh

We describe a method for training accurate Transformer machine-translation models to run inference using 8-bit integer (INT8) hardware matrix multipliers, as opposed to the more costly single-precision floating-point (FP32) hardware. Unlike…

Machine Learning · Computer Science 2021-05-17 Ephrem Wu

The growing demand for Large Language Models (LLMs) in applications such as content generation, intelligent chatbots, and sentiment analysis poses considerable challenges for LLM service providers. To efficiently use GPU resources and boost…

Machine Learning · Computer Science 2024-04-17 Yilong Zhao , Chien-Yu Lin , Kan Zhu , Zihao Ye , Lequn Chen , Size Zheng , Luis Ceze , Arvind Krishnamurthy , Tianqi Chen , Baris Kasikci

Transformer-based models have gained widespread popularity in both the computer vision (CV) and natural language processing (NLP) fields. However, significant challenges arise during post-training linear quantization, leading to noticeable…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Jiun-Man Chen , Yu-Hsuan Chao , Yu-Jie Wang , Ming-Der Shieh , Chih-Chung Hsu , Wei-Fen Lin

Achieving reliable 4-bit attention is a prerequisite for end-to-end FP4 computation on emerging FP4-capable GPUs, yet attention remains the main obstacle due to FP4's tiny dynamic range and attention's heavy-tailed activations. This paper…

Machine Learning · Computer Science 2026-03-10 Peiyuan Zhang , Matthew Noto , Wenxuan Tan , Chengquan Jiang , Will Lin , Wei Zhou , Hao Zhang

The inference of Large language models (LLMs) requires immense computation and memory resources. To curtail these costs, quantisation has merged as a promising solution, but existing LLM quantisation mainly focuses on 8-bit. In this work,…

Machine Learning · Computer Science 2024-03-15 Cheng Zhang , Jianyi Cheng , Ilia Shumailov , George A. Constantinides , Yiren Zhao

8-bit integer inference, as a promising direction in reducing both the latency and storage of deep neural networks, has made great progress recently. On the other hand, previous systems still rely on 32-bit floating point for certain…

Computation and Language · Computer Science 2020-09-21 Ye Lin , Yanyang Li , Tengbo Liu , Tong Xiao , Tongran Liu , Jingbo Zhu

Reinforcement learning (RL) for large language models (LLMs) is increasingly bottlenecked by rollout (generation), where long output sequence lengths make attention and KV-cache memory dominate end-to-end step time. FP8 offers an attractive…

Machine Learning · Computer Science 2026-04-13 Zhaopeng Qiu , Shuang Yu , Jingqi Zhang , Shuai Zhang , Xue Huang , Jingyi Yang , Junjie Lai

Researches have demonstrated that low bit-width (e.g., INT8) quantization can be employed to accelerate the inference process. It makes the gradient quantization very promising since the backward propagation requires approximately twice…

Computer Vision and Pattern Recognition · Computer Science 2021-02-10 Kang Zhao , Sida Huang , Pan Pan , Yinghan Li , Yingya Zhang , Zhenyu Gu , Yinghui Xu

The immense computational cost of training Large Language Models (LLMs) presents a major barrier to innovation. While FP8 training offers a promising solution with significant theoretical efficiency gains, its widespread adoption has been…

Computation and Language · Computer Science 2025-10-20 Wenjun Wang , Shuo Cai , Congkai Xie , Mingfa Feng , Yiming Zhang , Zhen Li , Kejing Yang , Ming Li , Jiannong Cao , Hongxia Yang

We present LLMQ, an end-to-end CUDA/C++ implementation for medium-sized language-model training, e.g. 3B to 32B parameters, on affordable, commodity GPUs. These devices are characterized by low memory availability and slow communication…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-18 Erik Schultheis , Dan Alistarh

We demonstrate, for the first time, fully quantized training (FQT) of large language models (LLMs) using predominantly 4-bit floating-point (FP4) precision for weights, activations, and gradients on datasets up to 200 billion tokens. We…

Machine Learning · Computer Science 2025-08-12 Brian Chmiel , Maxim Fishman , Ron Banner , Daniel Soudry

Large Language Model training with 8-bit floating point (FP8) formats promises significant efficiency improvements, but reduced numerical precision makes training challenging. It is currently possible to train in FP8 only if one is willing…

Machine Learning · Computer Science 2025-06-06 Saaketh Narayan , Abhay Gupta , Mansheej Paul , Davis Blalock

Recent advances in self-supervised learning and the Transformer architecture have significantly improved natural language processing (NLP), achieving remarkably low perplexity. However, the growing size of NLP models introduces a memory…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-04-02 Gunho Park , Baeseong Park , Minsub Kim , Sungjae Lee , Jeonghoon Kim , Beomseok Kwon , Se Jung Kwon , Byeongwook Kim , Youngjoo Lee , Dongsoo Lee

Quantization has become a crucial step for the efficient deployment of deep neural networks, where floating point operations are converted to simpler fixed point operations. In its most naive form, it simply consists in a combination of…

Machine Learning · Computer Science 2023-08-16 Edouard Yvinec , Arnaud Dapogny , Kevin Bailly

This paper presents an optimized methodology to design and deploy Speech Enhancement (SE) algorithms based on Recurrent Neural Networks (RNNs) on a state-of-the-art MicroController Unit (MCU), with 1+8 general-purpose RISC-V cores. To…

Sound · Computer Science 2022-10-17 Manuele Rusci , Marco Fariselli , Martin Croome , Francesco Paci , Eric Flamand

The 8 bits quantization has been widely applied to accelerate network inference in various deep learning applications. There are two kinds of quantization methods, training-based quantization and post-training quantization. Training-based…

Computer Vision and Pattern Recognition · Computer Science 2020-07-01 Di Wu , Qi Tang , Yongle Zhao , Ming Zhang , Ying Fu , Debing Zhang

Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often fail to concurrently speed up the prefill and decoding…

Machine Learning · Computer Science 2024-08-01 Ying Zhang , Peng Zhang , Mincong Huang , Jingyang Xiang , Yujie Wang , Chao Wang , Yineng Zhang , Lei Yu , Chuan Liu , Wei Lin

Classical simulation of quantum circuits remains indispensable for algorithm development, hardware validation, and error analysis in the noisy intermediate-scale quantum (NISQ) era. However, state-vector simulation faces exponential memory…

Large language models (LLMs) have demonstrated impressive abilities in various domains while the inference cost is expensive. Many previous studies exploit quantization methods to reduce LLM inference cost by reducing latency and memory…

Machine Learning · Computer Science 2024-11-12 Jinhao Li , Jiaming Xu , Shiyao Li , Shan Huang , Jun Liu , Yaoxiu Lian , Guohao Dai