Enabling Resource-Efficient On-Device Fine-Tuning of LLMs Using Only Inference Engines

Large Language Models (LLMs) have demonstrated exceptional performance in automating various tasks, such as text generation and summarization. Currently LLMs are trained and fine-tuned on large cloud server. Deploying and fine-tuning these models on resource-constrained edge devices remains a significant challenge due to their substantial memory and computational requirements. This paper introduces a computation-efficient zeroth-order optimization approach that lowers the barriers for fine-tuning LLMs in such constrained environments. Our method features a parallelized randomized gradient estimation (P-RGE) technique, which performs gradient estimation with high parallel efficiency. P-RGE leverages outer-loop and inner-loop parallelization to perform multiple function queries and forward passes in parallel, reducing the wall-clock end-to-end training time. By integrating this technique with parameter-efficient fine-tuning methods (e.g., LoRA) and on-device inference engines (e.g., ExecuTorch), we demonstrate efficient fine-tuning of LLMs on both server-side and edge devices. Experiments show that P-RGE achieves significant runtime speedups and memory savings while maintaining fine-tuning accuracy, which paves the way for more practical deployment of LLMs in real-time, on-device applications.