Performance Testing and Analysis of Token Generation for LLMs Based on MaaS (Model-as-a-Service)

Yang Cheng, Sisi Qin, Jing Qi, Feng Cao, Dongwei Yan. Performance Testing and Analysis of Token Generation for LLMs Based on MaaS (Model-as-a-Service). In 2025 IEEE International Conference on High Performance Computing and Communications, HPCC 2025, Exeter, United Kingdom, August 13-15, 2025. pages 1417-1422, IEEE, 2025. [doi]

Abstract

Abstract is missing.