arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.14910cs.CLcs.AI
收藏

EvoP:基于进化剪枝的鲁棒LLM推理

EvoP: Robust LLM Inference via Evolutionary Pruning

City University of Hong Kong(香港城市大学);Mohamed bin Zayed University of Artificial Intelligence(马尔代夫穆罕默德·本·扎耶德人工智能大学);Baidu(百度);National Taiwan University(国立台湾大学)

Shangyu Wu, Hongchao Du, Ying Xiong, Shuai Chen, Tei-Wei Kuo, Nan Guan, Chun Jason Xue

AI总结:

针对现有LLM剪枝方法因启发式策略和忽略数据特征导致性能次优的问题,提出进化剪枝框架EvoP,通过CCDS策略构建多样校准集并利用EPPS方法搜索最优剪枝模式,在保持最佳效率的同时实现最佳性能,为资源受限环境下的LLM部署提供实用可扩展方案。

摘要:

大型语言模型(LLMs)在自然语言处理任务中取得了显著成功,但其庞大的模型规模和计算需求阻碍了在资源受限环境中的部署。现有模型剪枝方法通过移除模型中的冗余结构(如元素、通道、层)来解决此问题。然而,这些方法采用启发式剪枝策略,导致性能次优。此外,它们在剪枝时还忽略了数据特征。为克服这些局限,我们提出了EvoP,一个用于鲁棒LLM推理的进化剪枝框架。EvoP首先提出基于聚类的校准数据集采样(CCDS)策略,以创建更具多样性的校准数据集。EvoP随后引入进化剪枝模式搜索(EPPS)方法,以寻找最优剪枝模式。与现有模型剪枝技术相比,EvoP在保持最佳效率的同时实现了最佳性能。在不同LLMs和不同下游任务上的实验验证了所提出的EvoP的有效性,使其成为在现实应用中部署LLMs的实用且可扩展的解决方案。

英文摘要:

Large Language Models (LLMs) have achieved remarkable success in natural language processing tasks, but their massive size and computational demands hinder their deployment in resource-constrained environments. Existing model pruning methods address this issue by removing redundant structures (e.g., elements, channels, layers) from the model. However, these methods employ a heuristic pruning strategy, which leads to suboptimal performance. Besides, they also ignore the data characteristics when pruning the model. To overcome these limitations, we propose EvoP, an evolutionary pruning framework for robust LLM inference. EvoP first presents a cluster-based calibration dataset sampling (CCDS) strategy for creating a more diverse calibration dataset. EvoP then introduces an evolutionary pruning pattern searching (EPPS) method to find the optimal pruning pattern. Compared to existing model pruning techniques, EvoP achieves the best performance while maintaining the best efficiency. Experiments across different LLMs and different downstream tasks validate the effectiveness of the proposed EvoP, making it a practical and scalable solution for deploying LLMs in real-world applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑