Inference Performance Optimization for Large Language Models on CPUs

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: He, Pujiang, Zhou, Shan, Huang, Wenhuan, Li, Changqing, Wang, Duyi, Guo, Bin, Meng, Chen, Gui, Sheng, Yu, Weifei, Xie, Yi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917717633662976
author He, Pujiang
Zhou, Shan
Huang, Wenhuan
Li, Changqing
Wang, Duyi
Guo, Bin
Meng, Chen
Gui, Sheng
Yu, Weifei
Xie, Yi
author_facet He, Pujiang
Zhou, Shan
Huang, Wenhuan
Li, Changqing
Wang, Duyi
Guo, Bin
Meng, Chen
Gui, Sheng
Yu, Weifei
Xie, Yi
contents Large language models (LLMs) have shown exceptional performance and vast potential across diverse tasks. However, the deployment of LLMs with high performance in low-resource environments has garnered significant attention in the industry. When GPU hardware resources are limited, we can explore alternative options on CPUs. To mitigate the financial burden and alleviate constraints imposed by hardware resources, optimizing inference performance is necessary. In this paper, we introduce an easily deployable inference performance optimization solution aimed at accelerating LLMs on CPUs. In this solution, we implement an effective way to reduce the KV cache size while ensuring precision. We propose a distributed inference optimization approach and implement it based on oneAPI Collective Communications Library. Furthermore, we propose optimization approaches for LLMs on CPU, and conduct tailored optimizations for the most commonly used models. The code is open-sourced at https://github.com/intel/xFasterTransformer.
format Preprint
id arxiv_https___arxiv_org_abs_2407_07304
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Inference Performance Optimization for Large Language Models on CPUs
He, Pujiang
Zhou, Shan
Huang, Wenhuan
Li, Changqing
Wang, Duyi
Guo, Bin
Meng, Chen
Gui, Sheng
Yu, Weifei
Xie, Yi
Artificial Intelligence
Large language models (LLMs) have shown exceptional performance and vast potential across diverse tasks. However, the deployment of LLMs with high performance in low-resource environments has garnered significant attention in the industry. When GPU hardware resources are limited, we can explore alternative options on CPUs. To mitigate the financial burden and alleviate constraints imposed by hardware resources, optimizing inference performance is necessary. In this paper, we introduce an easily deployable inference performance optimization solution aimed at accelerating LLMs on CPUs. In this solution, we implement an effective way to reduce the KV cache size while ensuring precision. We propose a distributed inference optimization approach and implement it based on oneAPI Collective Communications Library. Furthermore, we propose optimization approaches for LLMs on CPU, and conduct tailored optimizations for the most commonly used models. The code is open-sourced at https://github.com/intel/xFasterTransformer.
title Inference Performance Optimization for Large Language Models on CPUs
topic Artificial Intelligence
url https://arxiv.org/abs/2407.07304