paper-with-me

Papers

CDM-QTA: Quantized Training Acceleration for Efficient LoRA Fine-Tuning of Diffusion Model

2025-04-08 · Jinming Lu, Minghao She, Wendong Mao, Zhongfeng Wang

Fine-tuning large diffusion models for custom applications demands substantial power and time, which poses significant challenges for efficient implementation on mobile devices. In this paper, we develop a novel training accelerator specifically for Low-Rank Adaptation (LoRA) of diffusion models, aiming to streamline the process and reduce computational complexity. By leveraging a fully quantized training scheme for LoRA fine-tuning, we achieve substantial reductions in memory usage and power consumption while maintaining high model fidelity. The proposed accelerator features flexible dataflow, enabling high utilization for irregular and variable tensor shapes during the LoRA process. Experimental results show up to 1.81x training speedup and 5.50x energy efficiency improvements compared to the baseline, with minimal impact on image generation quality.

📄 PDF Abstract BibTeX arXiv:2504.07998

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic

2025-10-28 · Kanghyun Choi, Hyeyoon Lee, SunJong Park, Dain Kwon 외 arxiv

Low-bit floating-point (FP) formats, such as FP8, provide significant acceleration and memory savings in model training thanks to native hardware support on modern GPUs and NPUs. However, we analyze that FP8 quantization…

IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models

2024-10-29 · Hang Guo, Yawei Li, Tao Dai, Shu-Tao Xia 외

Fine-tuning pre-trained diffusion models under limited budgets has gained great success. In particular, the recent advances that directly fine-tune the quantized weights using Low-rank Adaptation (LoRA) further reduces t…

parameter-efficient fine-tuningQuantization

QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning

2024-02-16 · Hossein Rajabzadeh, Mojtaba Valipour, Tianshu Zhu, Marzieh Tahaei 외

Finetuning large language models requires huge GPU memory, restricting the choice to acquire Larger models. While the quantized version of the Low-Rank Adaptation technique, named QLoRA, significantly alleviates this iss…

GPULanguage ModelingLanguage ModellingLarge Language Model+1

CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization

2025-01-30 · Yanxia Deng, Aozhong zhang, Naigang Wang, Selcuk Gurses 외

Fine-tuning large language models (LLMs) using low-rank adaptation (LoRA) has become a highly efficient approach for downstream tasks, particularly in scenarios with limited computational resources. However, applying LoR…

Arithmetic ReasoningText Generation

Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

2024-02-08 · Haotong Qin, Xudong Ma, Xingyu Zheng, Xiaoyang Li 외

The LoRA-finetuning quantization of LLMs has been extensively studied to obtain accurate yet compact LLMs for deployment on resource-constrained hardware. However, existing methods cause the quantized LLM to severely deg…

MMLUQuantization