MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures
This addresses deployment challenges for LLMs by enabling efficient pruning without sacrificing uniform structures, though it is incremental as it builds on existing structured pruning techniques.
The paper tackles the problem of structured pruning for large language models (LLMs) by proposing a mask-based method to maintain uniform layer-wise structures, which enhances inference efficiency and compatibility with acceleration techniques. Experimental results show it outperforms state-of-the-art methods while preserving high performance.
The remarkable performance of large language models (LLMs) in various language tasks has attracted considerable attention. However, the ever-increasing size of these models presents growing challenges for deployment and inference. Structured pruning, an effective model compression technique, is gaining increasing attention due to its ability to enhance inference efficiency. Nevertheless, most previous optimization-based structured pruning methods sacrifice the uniform structure across layers for greater flexibility to maintain performance. The heterogeneous structure hinders the effective utilization of off-the-shelf inference acceleration techniques and impedes efficient configuration for continued training. To address this issue, we propose a novel masking learning paradigm based on minimax optimization to obtain the uniform pruned structure by optimizing the masks under sparsity regularization. Extensive experimental results demonstrate that our method can maintain high performance while ensuring the uniformity of the pruned model structure, thereby outperforming existing SOTA methods.