saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-28 20:11:22 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/onnxruntime/contrib_ops/cuda
History
Vincent Wang 4df356d1c9
Train BERT Using BFloat16 on A100 (#6090) 
* traing bert using bf16

* Adam support bf16

* bugfix

* add fusedmatmul support

* fix after merge from master.

* bugfix

* bugfix after merge from master

* fast reduction for bf16.

* resolve comments

* fix win build

* bugfix

* change header file.

Co-authored-by: Vincent Wang <weicwang@microsoft.com>
2021-01-14 19:04:32 +08:00
..
activation Check status of element-wise op prepare functions. (#4830) 2020-08-17 16:11:30 -07:00
bert Train BERT Using BFloat16 on A100 (#6090) 2021-01-14 19:04:32 +08:00
math Train BERT Using BFloat16 on A100 (#6090) 2021-01-14 19:04:32 +08:00
quantization Reduce amount of compiled CUDA device code (#6118) 2020-12-14 15:27:40 -08:00
tensor Reduce amount of compiled CUDA device code (#6118) 2020-12-14 15:27:40 -08:00
conv_transpose_with_dynamic_pads.cc Adding custom op ConvTransposeWithDynamicPads. (#638) 2019-05-31 11:48:43 -07:00
conv_transpose_with_dynamic_pads.h Adding custom op ConvTransposeWithDynamicPads. (#638) 2019-05-31 11:48:43 -07:00
cuda_contrib_kernels.cc Train BERT Using BFloat16 on A100 (#6090) 2021-01-14 19:04:32 +08:00
cuda_contrib_kernels.h move cpu/cuda related files to coresponding cpu/cuda folder (#3668) 2020-04-24 00:12:02 -07:00
inverse.cc Reduce amount of compiled CUDA device code (#6118) 2020-12-14 15:27:40 -08:00
layer_norm.cc Train BERT Using BFloat16 on A100 (#6090) 2021-01-14 19:04:32 +08:00
layer_norm.h Reduce amount of compiled CUDA device code (#6118) 2020-12-14 15:27:40 -08:00
layer_norm_impl.cu Train BERT Using BFloat16 on A100 (#6090) 2021-01-14 19:04:32 +08:00
layer_norm_impl.h Simplified layer norm changes (#5028) 2020-10-12 11:22:12 -07:00