carlushuang 4e9b76f88c [CK_TILE] optimize moe sorting kernel, boost large context case up to 20x (#2153) ...

* combine 2-3 as single stage

* support zeroing

* improve long tokens

* update specialization

* b16 ws

* 8bit topk optimize

* update 15 example

2025-05-06 17:32:07 +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] optimize moe sorting kernel, boost large context case up to 20x (#2153)

2025-05-06 17:32:07 +08:00

moe_sorting_problem.hpp

[CK_TILE] optimize moe sorting kernel, boost large context case up to 20x (#2153)

2025-05-06 17:32:07 +08:00