Inference Performance Optimization for Large Language Models on CPUs

TL;DR

This paper presents a practical optimization method for accelerating large language model inference on CPUs, focusing on reducing KV cache size and implementing distributed inference to improve performance in resource-constrained environments.

Contribution

It introduces a novel, easily deployable CPU inference optimization technique, including KV cache reduction and distributed inference, with tailored solutions for popular models.

Findings

Significant speedup in LLM inference on CPUs

Effective KV cache size reduction without losing accuracy

Open-source implementation available

Abstract

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.