onnxruntime/onnxruntime
Tianlei Wu 8b0e0f4927
Add RemovePadding and RestorePadding for BERT model (#13701)
Add two operators RemovePadding and RestorePadding based on ideal of
effective transformer (https://github.com/bytedance/effective_transformer) to improve large
batch size inference for BERT model.
2022-11-22 10:00:23 -08:00
..
contrib_ops Add RemovePadding and RestorePadding for BERT model (#13701) 2022-11-22 10:00:23 -08:00
core Add RemovePadding and RestorePadding for BERT model (#13701) 2022-11-22 10:00:23 -08:00
python [ROCm] Add GemmFastGelu TunableOp (#13589) 2022-11-22 12:58:01 +08:00
test Add RemovePadding and RestorePadding for BERT model (#13701) 2022-11-22 10:00:23 -08:00
tool/etw
wasm [js/web] add 'xnnpack' to EP list (#12723) 2022-10-03 10:38:45 -07:00
__init__.py Bumping up version number to 1.14.0 on main branch (#13401) 2022-10-21 19:16:44 -04:00
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings