Michael Mcminn afe1ff618d Ud fix moe sorting gfx908 (#2720) ...

* Adding a ds permute fallback for the gfx908 and older for row_newbcast:7 instruction

* Better macro for selecting ROW_NEWBCAST

* clang-format the update

---------

Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>

2025-11-03 07:31:31 -08:00

..

fused_moegemm_kernel.hpp

Fix for Add the API to load SGPR (#2913)

2025-09-25 10:32:42 -07:00

fused_moegemm_shape.hpp

[CK_TILE] Fix compilation errors introduced in #2320, #2219 and #2214 (#2388)

2025-06-23 12:29:15 +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

Ud fix moe sorting gfx908 (#2720)

2025-11-03 07:31:31 -08:00

moe_sorting_problem.hpp

[CK_TILE] moe sorting optimize local_token (#2469)

2025-07-15 09:42:18 +08:00