MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Yanyue, Zhang, Zhi, Zhou, Ding, Xie, Cong, Song, Ziang, Liu, Xin, Wang, Yanzhi, Lin, Xue, Xu, An
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917804654985216
author Xie, Yanyue
Zhang, Zhi
Zhou, Ding
Xie, Cong
Song, Ziang
Liu, Xin
Wang, Yanzhi
Lin, Xue
Xu, An
author_facet Xie, Yanyue
Zhang, Zhi
Zhou, Ding
Xie, Cong
Song, Ziang
Liu, Xin
Wang, Yanzhi
Lin, Xue
Xu, An
contents Mixture-of-Experts (MoE) architectures face challenges such as high memory consumption and redundancy in experts. Pruning MoE can reduce network weights while maintaining model performance. Motivated by the recent observation of emergent large magnitude features in Large Language Models (LLM) and MoE routing policy, we propose MoE-Pruner, a method that prunes weights with the smallest magnitudes multiplied by the corresponding input activations and router weights, on each output neuron. Our pruning method is one-shot, requiring no retraining or weight updates. We evaluate our method on Mixtral-8x7B and Mixtral-8x22B across multiple language benchmarks. Experimental results show that our pruning method significantly outperforms state-of-the-art LLM pruning methods. Furthermore, our pruned MoE models can benefit from a pretrained teacher model through expert-wise knowledge distillation, improving performance post-pruning. Experimental results demonstrate that the Mixtral-8x7B model with 50% sparsity maintains 99% of the performance of the original model after the expert-wise knowledge distillation.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12013
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router
Xie, Yanyue
Zhang, Zhi
Zhou, Ding
Xie, Cong
Song, Ziang
Liu, Xin
Wang, Yanzhi
Lin, Xue
Xu, An
Computation and Language
Artificial Intelligence
Machine Learning
Mixture-of-Experts (MoE) architectures face challenges such as high memory consumption and redundancy in experts. Pruning MoE can reduce network weights while maintaining model performance. Motivated by the recent observation of emergent large magnitude features in Large Language Models (LLM) and MoE routing policy, we propose MoE-Pruner, a method that prunes weights with the smallest magnitudes multiplied by the corresponding input activations and router weights, on each output neuron. Our pruning method is one-shot, requiring no retraining or weight updates. We evaluate our method on Mixtral-8x7B and Mixtral-8x22B across multiple language benchmarks. Experimental results show that our pruning method significantly outperforms state-of-the-art LLM pruning methods. Furthermore, our pruned MoE models can benefit from a pretrained teacher model through expert-wise knowledge distillation, improving performance post-pruning. Experimental results demonstrate that the Mixtral-8x7B model with 50% sparsity maintains 99% of the performance of the original model after the expert-wise knowledge distillation.
title MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2410.12013