"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference."

Hyungjun Oh et al. (2024)

Details and statistics

DOI: 10.1145/3620665.3640383

access: closed

type: Conference or Workshop Paper

metadata version: 2024-05-04

a service of  Schloss Dagstuhl - Leibniz Center for Informatics