feli dc656b04d8 ck moe gemm implement (#1936) ...

* port all moe changes from ck_moe_gemm branch

* refine codes in the pr

* fix tail odd

* fix clang format

* fix clang format2

* make hot loop scheduler compatible with 16x16 and 32x32

* clang format

* fix per token quant

* rename moe example

* clang format

---------

Co-authored-by: coderfeli <coderfeli@163.com>

[ROCm/composable_kernel commit: 3786e16375]

2025-03-05 15:56:55 +08:00

..

ck

ck moe gemm implement (#1936)

2025-03-05 15:56:55 +08:00

ck_tile

Missing _ in __HIPCC__ (#1930)

2025-03-03 08:19:47 -08:00