Skip to content

SAP-BERT: BERT Inference Acceleration Through Skip-Layer and Adaptive Patient Early Exiting.

Lei Jiang, Yan Tan, Jiaqian Ren, Kun Peng, Haimei Qin, Chaodong Tong, Gao Jiayang

VenueBICONIP
Year2024
ProceedingsICONIP (10)

Browse the full ICONIP paper archive.