Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gul, Hongyaoxing, Hu, Lijuan, Niu, Shuzi, Liu, Fangfang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.05684
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908754904088576
author Gul, Hongyaoxing
Hu, Lijuan
Niu, Shuzi
Liu, Fangfang
author_facet Gul, Hongyaoxing
Hu, Lijuan
Niu, Shuzi
Liu, Fangfang
contents Traditional post-training quantization (PTQ) is considered an effective approach to reduce model size and accelerate inference of large-scale language models (LLMs). However, existing low-rank PTQ methods require costly fine-tuning to determine a compromise rank for diverse data and layers in large models, failing to exploit their full potential. Additionally, the current SVD-based low-rank approximation compounds the computational overhead. In this work, we thoroughly analyze the varying effectiveness of low-rank approximation across different layers in representative models. Accordingly, we introduce \underline{F}lexible \underline{L}ow-\underline{R}ank \underline{Q}uantization (FLRQ), a novel solution designed to quickly identify the accuracy-optimal ranks and aggregate them to achieve minimal storage combinations. FLRQ comprises two powerful components, Rank1-Sketch-based Flexible Rank Selection (R1-FLR) and Best Low-rank Approximation under Clipping (BLC). R1-FLR applies the R1-Sketch with Gaussian projection for the fast low-rank approximation, enabling outlier-aware rank extraction for each layer. Meanwhile, BLC aims at minimizing the low-rank quantization error under the scaling and clipping strategy through an iterative method. FLRQ demonstrates strong effectiveness and robustness in comprehensive experiments, achieving state-of-the-art performance in both quantization quality and algorithm efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05684
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FLRQ: Faster LLM Quantization with Flexible Low-Rank Matrix Sketching
Gul, Hongyaoxing
Hu, Lijuan
Niu, Shuzi
Liu, Fangfang
Machine Learning
Traditional post-training quantization (PTQ) is considered an effective approach to reduce model size and accelerate inference of large-scale language models (LLMs). However, existing low-rank PTQ methods require costly fine-tuning to determine a compromise rank for diverse data and layers in large models, failing to exploit their full potential. Additionally, the current SVD-based low-rank approximation compounds the computational overhead. In this work, we thoroughly analyze the varying effectiveness of low-rank approximation across different layers in representative models. Accordingly, we introduce \underline{F}lexible \underline{L}ow-\underline{R}ank \underline{Q}uantization (FLRQ), a novel solution designed to quickly identify the accuracy-optimal ranks and aggregate them to achieve minimal storage combinations. FLRQ comprises two powerful components, Rank1-Sketch-based Flexible Rank Selection (R1-FLR) and Best Low-rank Approximation under Clipping (BLC). R1-FLR applies the R1-Sketch with Gaussian projection for the fast low-rank approximation, enabling outlier-aware rank extraction for each layer. Meanwhile, BLC aims at minimizing the low-rank quantization error under the scaling and clipping strategy through an iterative method. FLRQ demonstrates strong effectiveness and robustness in comprehensive experiments, achieving state-of-the-art performance in both quantization quality and algorithm efficiency.
title FLRQ: Faster LLM Quantization with Flexible Low-Rank Matrix Sketching
topic Machine Learning
url https://arxiv.org/abs/2601.05684