Iterative Layer Pruning for Efficient Translation Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Moslem, Yasmin, Farouq, Muhammad Hazim Al, Kelleher, John D.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914116155736064
author Moslem, Yasmin
Farouq, Muhammad Hazim Al
Kelleher, John D.
author_facet Moslem, Yasmin
Farouq, Muhammad Hazim Al
Kelleher, John D.
contents Large language models (LLMs) have transformed many areas of natural language processing, including machine translation. However, efficient deployment of LLMs remains challenging due to their intensive computational requirements. In this paper, we address this challenge and present our submissions to the Model Compression track at the Conference on Machine Translation (WMT 2025). In our experiments, we investigate iterative layer pruning guided by layer importance analysis. We evaluate this method using the Aya-Expanse-8B model for translation from Czech to German, and from English to Egyptian Arabic. Our approach achieves substantial reductions in model size and inference time, while maintaining the translation quality of the baseline models.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22763
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Iterative Layer Pruning for Efficient Translation Inference
Moslem, Yasmin
Farouq, Muhammad Hazim Al
Kelleher, John D.
Computation and Language
Performance
Large language models (LLMs) have transformed many areas of natural language processing, including machine translation. However, efficient deployment of LLMs remains challenging due to their intensive computational requirements. In this paper, we address this challenge and present our submissions to the Model Compression track at the Conference on Machine Translation (WMT 2025). In our experiments, we investigate iterative layer pruning guided by layer importance analysis. We evaluate this method using the Aya-Expanse-8B model for translation from Czech to German, and from English to Egyptian Arabic. Our approach achieves substantial reductions in model size and inference time, while maintaining the translation quality of the baseline models.
title Iterative Layer Pruning for Efficient Translation Inference
topic Computation and Language
Performance
url https://arxiv.org/abs/2510.22763