Saved in:
Bibliographic Details
Main Authors: Chen, Yushuo, Tang, Tianyi, Xiang, Erge, Li, Linjiang, Zhao, Wayne Xin, Wang, Jing, Chai, Yunpeng, Wen, Ji-Rong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.11502
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911844188291072
author Chen, Yushuo
Tang, Tianyi
Xiang, Erge
Li, Linjiang
Zhao, Wayne Xin
Wang, Jing
Chai, Yunpeng
Wen, Ji-Rong
author_facet Chen, Yushuo
Tang, Tianyi
Xiang, Erge
Li, Linjiang
Zhao, Wayne Xin
Wang, Jing
Chai, Yunpeng
Wen, Ji-Rong
contents In real world, large language models (LLMs) can serve as the assistant to help users accomplish their jobs, and also support the development of advanced applications. For the wide application of LLMs, the inference efficiency is an essential concern, which has been widely studied in existing work, and numerous optimization algorithms and code libraries have been proposed to improve it. Nonetheless, users still find it challenging to compare the effectiveness of all the above methods and understand the underlying mechanisms. In this work, we perform a detailed coarse-to-fine analysis of the inference performance of various code libraries. To evaluate the overall effectiveness, we examine four usage scenarios within two practical applications. We further provide both theoretical and empirical fine-grained analyses of each module in the Transformer architecture. Our experiments yield comprehensive results that are invaluable for researchers to evaluate code libraries and improve inference strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2404_11502
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models
Chen, Yushuo
Tang, Tianyi
Xiang, Erge
Li, Linjiang
Zhao, Wayne Xin
Wang, Jing
Chai, Yunpeng
Wen, Ji-Rong
Computation and Language
Artificial Intelligence
In real world, large language models (LLMs) can serve as the assistant to help users accomplish their jobs, and also support the development of advanced applications. For the wide application of LLMs, the inference efficiency is an essential concern, which has been widely studied in existing work, and numerous optimization algorithms and code libraries have been proposed to improve it. Nonetheless, users still find it challenging to compare the effectiveness of all the above methods and understand the underlying mechanisms. In this work, we perform a detailed coarse-to-fine analysis of the inference performance of various code libraries. To evaluate the overall effectiveness, we examine four usage scenarios within two practical applications. We further provide both theoretical and empirical fine-grained analyses of each module in the Transformer architecture. Our experiments yield comprehensive results that are invaluable for researchers to evaluate code libraries and improve inference strategies.
title Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2404.11502