ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference

Open Webpage

Hyungjun Oh, Kihong Kim, Jaemin Kim, Sungkyun Kim, Junyeol Lee, Du-Seong Chang, Jiwon Seo

Published: 2024, Last Modified: 06 Jan 2026ASPLOS (2) 2024EveryoneRevisionsBibTeXCC BY-SA 4.0