FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic
This provides a practical solution for efficient fine-tuning of large language models, though it is incremental as it builds on existing LoRA and quantization techniques.
The paper tackles the limited speedup of FP8 quantization in LoRA fine-tuning due to overheads, proposing FALQON to merge LoRA adapters into an FP8-quantized backbone, achieving approximately 3x training speedup over existing quantized LoRA methods with similar accuracy.
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 offers speedup primarily for large-dimensional matrix multiplications, while inherent quantization overheads diminish speedup when applied to low-rank adaptation (LoRA), which uses small-dimensional matrices for efficient fine-tuning of large language models (LLMs). To address this limitation, we propose FALQON, a novel framework that eliminates the quantization overhead from separate LoRA computational paths by directly merging LoRA adapters into an FP8-quantized backbone during fine-tuning. Furthermore, we reformulate the forward and backward computations for merged adapters to significantly reduce quantization overhead, and introduce a row-wise proxy update mechanism that efficiently integrates substantial updates into the quantized backbone. Experimental evaluations demonstrate that FALQON achieves approximately a 3$\times$ training speedup over existing quantized LoRA methods with a similar level of accuracy, providing a practical solution for efficient large-scale model fine-tuning. Moreover, FALQON's end-to-end FP8 workflow removes the need for post-training quantization, facilitating efficient deployment. Code is available at https://github.com/iamkanghyunchoi/falqon.