Optimize grouped conv bwd weight for small M and N (#1303)

Browse Source

* Optimize grouped conv bwd weight for small M and N

* Fixes

...

This commit is contained in:

Bartłomiej Kocot

2024-05-22 21:01:01 +02:00

committed by GitHub

parent 7b027d5643

commit fd72380aeb

18 changed files with 3219 additions and 383 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

1306

include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_two_stage_xdl_cshuffle.hpp

File diff suppressed because it is too large Load Diff