An Autonomous Parallelization of Transformer Model Inference on Heterogeneous Edge Devices.

Insung Bahk Juhyeon Lee Insung Bahk Hoseung Kim Sinjin Jeong Suyeon Lee Donghyun Min An Autonomous Parallelization of Transformer Model Inference on Heterogeneous Edge Devices. 50-61 2024 ICS https://doi.org/10.1145/3650200.3656628 https://www.wikidata.org/entity/Q130973600 conf/ics/2024 db/conf/ics/ics2024.html#LeeBKJLM24 Sinjin Jeong Hoseung Kim Juhyeon Lee Suyeon Lee Donghyun Min