LoRAExit: Empowering Dynamic Modulation of LLMs in Resource-limited Settings using Low-rank Adapters

Abstract

Large Language Models (LLMs) have exhibited remarkable performance across various natural language processing tasks. However, deploying LLMs on resource-limited settings remains a challenge. While early-exit techniques offer an effective approach, they often require compromised training methods that result in sub-optimal performance. On the other hand, multi-model methods achieve improved results but suffer from significant inference latency and memory consumption. In this paper, we propose LoRAExit, a novel dynamic inference architecture that leverages low-rank adaptors for efficient deployment of LLMs. LoRAExit decouples the training of multiple exit interfaces, enabling the separate optimization of each exit, thereby fundamentally addressing the performance issues of early-exit networks. Moreover, we introduce a superior-exit guided distillation method that effectively utilizes models of different sizes, thereby further enhancing the performance of early exits. Experimental results demonstrate that LoRAExit significantly improves LLM performance when deployed on resource-limited settings.