Exploring Memory Partitioning of LLMs for Faster Inference on CPUs
收藏官方服务：
资源简介：
Overview This repository contains the experimental logs, data, and analysis scripts accompanying the research paper: Exploring Memory Partitioning of LLMs for Faster Inference on CPUs Authors: Noureddine Bouhali, John Osorio, Etienne Renault Accepted in te 34th International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication System, 2026 Contents of this Repository: run_logs: Raw execution logs and benchmark outputs for the evaluated memory partitioning strategies (layer-wise and tensor-wise tiering).
提供机构：
Zenodo创建时间：
2026-09-17
