English
Related papers

Related papers: MicroMix: Efficient Mixed-Precision Quantization w…

200 papers

Existing low-bit Microscaling (MX) formats, such as MXFP4, often suffer from substantial accuracy degradation due to the use of a shared scaling factor with the Power-of-Two format. In this work, we explore strategies that introduce minimal…

Hardware Architecture · Computer Science 2026-01-29 Weiming Hu , Zihan Zhang , Haoyan Zhang , Chen Zhang , Cong Guo , Yu Feng , Tianchi Hu , Guanglin Li , Guipeng Hu , Junsong Wang , Jingwen Leng

Quantization has emerged as a mainstream approach for deploying Large Language Models (LLMs) on resource-constrained devices, yet compressing precision below 4-bit typically causes severe performance degradation or prohibitive retraining…

Machine Learning · Computer Science 2026-05-22 Shu-Hao Zhang , Le-Tong Huang , Xiang-Sheng Deng , Xin-Yi Zou , Chen Wu , Nan Li , Shao-Qun Zhang , Zhi-Hua Zhou

Quantization is a critical technique for accelerating LLM inference by reducing memory footprint and improving computational efficiency. Among various schemes, 4-bit weight and 8-bit activation quantization (W4A8) offers a strong balance…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-03 Huanqi Hu , Bowen Xiao , Shixuan Sun , Jianian Yin , Zhexi Zhang , Xiang Luo , Chengquan Jiang , Weiqi Xu , Xiaoying Jia , Xin Liu , Minyi Guo

LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a…

Machine Learning · Computer Science 2025-05-30 Coleman Hooper , Sehoon Kim , Hiva Mohammadzadeh , Michael W. Mahoney , Yakun Sophia Shao , Kurt Keutzer , Amir Gholami

Training large language models is an expensive, compute-bound process that must be repeated as models scale, algorithms improve, and new data is collected. To address this, next-generation hardware accelerators increasingly support…

Machine Learning · Computer Science 2025-06-27 Huangyuan Su , Mujin Kwun , Stephanie Gil , Sham Kakade , Nikhil Anand

Large Language Models (LLMs) have achieved state-of-the-art performance across various language tasks but pose challenges for practical deployment due to their substantial memory requirements. Furthermore, the latest generative models…

Machine Learning · Computer Science 2023-08-22 Young Jin Kim , Rawn Henry , Raffy Fahim , Hany Hassan Awadalla

Large Language Models (LLMs) pose significant hardware challenges related to memory requirements and computational ability. There are two mainstream quantization schemes for LLMs: coarse-grained ($\textit{e.g.,}$ channel-wise) quantization…

Artificial Intelligence · Computer Science 2023-10-10 Luoming Zhang , Wen Fei , Weijia Wu , Yefei He , Zhenyu Lou , Hong Zhou

This study examines 4-bit quantization methods like GPTQ in large language models (LLMs), highlighting GPTQ's overfitting and limited enhancement in Zero-Shot tasks. While prior works merely focusing on zero-shot measurement, we extend task…

Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters. Mixed-precision quantization mitigates this cost by allocating expert-wise bit-widths…

Machine Learning · Computer Science 2026-05-25 Jianing Deng , Song Wang , Dongwei Wang , Zijie Liu , Tianlong Chen , Huanrui Yang , Jingtong Hu

Large Language Models (LLMs) with multimodal capabilities have revolutionized vision-language tasks, but their deployment often requires huge memory and computational resources. While post-training quantization (PTQ) has successfully…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Shubhang Bhatnagar , Andy Xu , Kar-Han Tan , Narendra Ahuja

Large language models (LLMs) have shown immense potential across various domains, but their high memory requirements and inference costs remain critical challenges for deployment. Post-training quantization (PTQ) has emerged as a promising…

Machine Learning · Computer Science 2026-01-05 Tianyi Zhang , Anshumali Shrivastava

As Large Language Models (LLMs) scale, weight-only quantization (W4A16: 4-bit weights, 16-bit activations) becomes critical for reducing memory footprint with minimal accuracy loss. However, its efficient deployment on Huawei's Ascend 910…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-04 Yuanhong He , Peiyu Niu , Jun Chen , Chenchen Zhang , Chao Yang

Mixed-precision quantization is a popular approach for compressing deep neural networks (DNNs). However, it is challenging to scale the performance efficiently with mixed-precision DNNs given the current FPGA architecture and conventional…

Hardware Architecture · Computer Science 2023-11-07 Yuzong Chen , Jordan Dotzel , Mohamed S. Abdelfattah

As large language models (LLMs) grow in size and deployment scale, quantization has become an essential technique for reducing memory footprint and improving inference efficiency. However, existing quantization toolkits often lack…

Machine Learning · Computer Science 2025-12-01 Dong Liu , Yanxuan Yu

We introduce QUICK, a group of novel optimized CUDA kernels for the efficient inference of quantized Large Language Models (LLMs). QUICK addresses the shared memory bank-conflict problem of state-of-the-art mixed precision matrix…

Machine Learning · Computer Science 2024-02-16 Taesu Kim , Jongho Lee , Daehyun Ahn , Sarang Kim , Jiwoong Choi , Minkyu Kim , Hyungjun Kim

Modern AI hardware, such as Nvidia's Blackwell architecture, is increasingly embracing low-precision floating-point (FP) formats to handle the pervasive activation outliers in Large Language Models (LLMs). Despite this industry trend, a…

Machine Learning · Computer Science 2025-10-30 Mengzhao Chen , Meng Wu , Hui Jin , Zhihang Yuan , Jing Liu , Chaoyi Zhang , Yunshui Li , Jie Huang , Jin Ma , Zeyue Xue , Zhiheng Liu , Xingyan Bin , Ping Luo

Efficient deployment of large language models (LLMs) necessitates low-bit quantization to minimize model size and inference cost. While low-bit integer formats (e.g., INT8/INT4) have been the conventional choice, emerging low-bit…

Machine Learning · Computer Science 2023-05-23 Yijia Zhang , Lingran Zhao , Shijie Cao , Wenqiang Wang , Ting Cao , Fan Yang , Mao Yang , Shanghang Zhang , Ningyi Xu

Today, large language models have demonstrated their strengths in various tasks ranging from reasoning, code generation, and complex problem solving. However, this advancement comes with a high computational cost and memory requirements,…

Machine Learning · Computer Science 2026-03-26 Meriem Bouzouad , Yuan-Hao Chang , Jalil Boukhobza

Model quantization represents both parameters (weights) and intermediate values (activations) in a more compact format, thereby directly reducing both computational and memory cost in hardware. The quantization of recent large language…

Hardware Architecture · Computer Science 2024-04-22 Jianyi Cheng , Cheng Zhang , Zhewen Yu , Christos-Savvas Bouganis , George A. Constantinides , Yiren Zhao

A lot of recent progress has been made in ultra low-bit quantization, promising significant improvements in latency, memory footprint and energy consumption on edge devices. Quantization methods such as Learned Step Size Quantization can…