Although large language models (LLM) have achieved remarkable performance, their enormous parameter counts hinder deployment on resource-constrained hardware. Low-rank compression can reduce both memory usage and computational demand, but applying a uniform compression ratio across all layers often leads to significant performance degradation, and previous methods perform poorly during decoding. To address these issues, we propose the Fine-grained Low-Rank Compressor (FLRC), which efficiently determines an optimal rank allocation for each layer, and incorporates progressive low-rank decoding to maintain text generation quality. Comprehensive experiments on diverse benchmarks demonstrate the superiority of FLRC, achieving up to a 17% improvement in ROUGE-L on summarization tasks compared to state-of-the-art low-rank compression methods, establishing a more robust and efficient framework to improve LLM inference.
@article{arxiv.2510.09332,
title = {FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference},
author = {Yu-Chen Lu and Chong-Yan Chen and Chi-Chih Chang and Yu-Fang Hu and Kai-Chiang Wu},
journal= {arXiv preprint arXiv:2510.09332},
year = {2025}
}