carlushuang 353a612b44 [CK_TILE] add moe-sorting MP kernel (#1910) ...

* moe sorting ex

* fix bug for race condition

* fix bug and optimze large expert

* fix

* optimize with sub_token_oneshot

* support skip empty tokens for expert sorting

* update moe_sorting

* tidy code

* support mp kernel

* hint mp

* remove use less code

* porting to example 15

---------

Co-authored-by: valarLip <340077269@qq.com>

2025-02-25 17:56:55 +08:00

..

fused_moegemm_kernel.hpp

[CK_TILE] moe sorting ex kernel to support expert > 128 (#1840)

2025-02-11 17:49:17 +08:00

fused_moegemm_shape.hpp

[CK_TILE] fused-moe first version (#1634)

2024-11-26 11:14:56 +08:00

fused_moegemm_tile_partitioner.hpp

[CK_TILE] fused-moe first version (#1634)

2024-11-26 11:14:56 +08:00

moe_sorting_kernel.hpp

[CK_TILE] add moe-sorting MP kernel (#1910)

2025-02-25 17:56:55 +08:00

moe_sorting_problem.hpp

[CK_TILE] add moe-sorting MP kernel (#1910)

2025-02-25 17:56:55 +08:00