Numerical Pruning for Efficient Autoregressive Models
This addresses efficiency problems for users of autoregressive models in language and image generation, though it appears incremental as it builds on existing pruning approaches.
The paper tackles the high computational cost of decoder-only transformer models by proposing a training-free pruning method that uses Newton's method to compress weights, achieving state-of-the-art performance with reduced memory usage and faster generation speeds on GPUs.
Transformers have emerged as the leading architecture in deep learning, proving to be versatile and highly effective across diverse domains beyond language and image processing. However, their impressive performance often incurs high computational costs due to their substantial model size. This paper focuses on compressing decoder-only transformer-based autoregressive models through structural weight pruning to improve the model efficiency while preserving performance for both language and image generation tasks. Specifically, we propose a training-free pruning method that calculates a numerical score with Newton's method for the Attention and MLP modules, respectively. Besides, we further propose another compensation algorithm to recover the pruned model for better performance. To verify the effectiveness of our method, we provide both theoretical support and extensive experiments. Our experiments show that our method achieves state-of-the-art performance with reduced memory usage and faster generation speeds on GPUs.