Aviral Goel
bb41ea37e1
chore(copyright) update library wide CMakeLists.txt copyright header template ( #3313 )
...
* chore(copyright) update library wide CMakeLists.txt files copyright header template
* Fix build
---------
Co-authored-by: Sami Remes <samremes@amd.com >
[ROCm/composable_kernel commit: 004784ef98
2025-11-28 13:49:54 -08:00
AviralGoelAMD
158fec303c
chore(copyright): update copyright header for test directory
...
[ROCm/composable_kernel commit: 4e49e0228b
2025-11-19 17:43:28 -07:00
Mateusz Ozga
8eb813de42
[CK_TILE] Fixed multi-abd GEMM test, NaN problem ( #2979 )
...
* Multi-ABD NaN problem
* Rollback tests
---------
Co-authored-by: root <root@splinter-126-008d.aus.dcgpu >
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com >
Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com >
[ROCm/composable_kernel commit: da4247a6df
2025-10-28 15:53:36 +01:00
Illia Silin
9aa69136e7
fix clang format ( #2926 )
...
[ROCm/composable_kernel commit: 9f6fc9fe09
2025-09-25 09:35:35 -07:00
Thomas Ning
bdea637a15
Fix the gfx950 numerical errors ( #2911 )
...
* Update grouped_gemm example and pipeline
* find the root cause error in did not enable the transpose in gfx950 correctly
* Fix v3 pipeline, row and col major
* Disable f8 datatype tests, it fails on gfx950
* fix the abd test by clear the runtime argument unsupported
---------
Co-authored-by: AviralGoelAMD <aviral.goel@amd.com >
Co-authored-by: Mateusz Ozga <mateusz.ozga@amd.com >
[ROCm/composable_kernel commit: b159841a06
2025-09-23 22:54:52 -07:00
Mateusz Ozga
2a150508c8
[CK_TILE] Multiple-ABD GEMM example ( #2788 )
...
* Multi ABD - initial commit
* Clang-foramt fix
* block gemm, unify the name of CDataType
* Apply chnages to mem-pipeline
* Rollback prefix for DType and Layout
* Gemm Kernel Basic, rename
* WMMA config
* Grouped GEMM
* Clang-format
* Dropout, name
* Review v2
* Move element_wise fn to unnary, remov old ones fn
* clang-format
* Fix issue review
* WP operator adjust to universal gemm
* v2 prepare
* Remove unused comment
* Remove vectorsize
* Rollback
* Adjust pipeline for abd
* Shuffle argument
* CI-fail fix quant
* Fix ag_br pipeline
* Failing tests
* Typo
* Single argument support
[ROCm/composable_kernel commit: 30ab1d6a71
2025-09-19 01:14:11 +02:00
