Rostyslav Geyyer 1fd27d520f Fix bf8 conversion issues (#1003) ...

* Fix the conversion

* Add bf8 functionality

* Enable example on MI200 as well

2023-10-20 08:00:45 -05:00

..

block

Add fp8 @ bf8 gemm support and example (#933)

2023-10-02 16:39:03 -05:00

device

Misc fixes (#994)

2023-10-19 11:26:04 -05:00

element

Fix bf8 conversion issues (#1003)

2023-10-20 08:00:45 -05:00

grid

Layernorm and groupnorm support to save mean and inverse std in forward (#929)

2023-10-19 07:36:29 +08:00

thread

add vector_type support into thread_copy_v3r1 (#969)

2023-10-13 15:11:43 -05:00

warp

Clean DTYPES conditions in CMake (#974)

2023-10-18 11:14:14 -05:00