SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models
This addresses the inference bottleneck for users of large language models, offering a scalable optimization method, though it is incremental as it builds on existing pruning techniques.
The paper tackles the high computational cost of Large Language Models during inference by introducing SEAP, a training-free pruning method that reduces computational overhead while maintaining competitive accuracy, achieving over 20% improvement over baseline methods at 50% pruning and only a 2.2% performance drop at 20% pruning.
Large Language Models have achieved remarkable success across various natural language processing tasks, yet their high computational cost during inference remains a major bottleneck. This paper introduces Sparse Expert Activation Pruning (SEAP), a training-free pruning method that selectively retains task-relevant parameters to reduce inference overhead. Inspired by the clustering patterns of hidden states and activations in LLMs, SEAP identifies task-specific expert activation patterns and prunes the model while preserving task performance and enhancing computational efficiency. Experimental results demonstrate that SEAP significantly reduces computational overhead while maintaining competitive accuracy. Notably, at 50% pruning, SEAP surpasses both WandA and FLAP by over 20%, and at 20% pruning, it incurs only a 2.2% performance drop compared to the dense model. These findings highlight SEAP's scalability and effectiveness, making it a promising approach for optimizing large-scale LLMs.