linqunAMD c254f3d7b4 [CK_TILE] Refine Generic2dBlockShape to fix ck_tile example 2,10,11,14 on rdna3 and 4 (#2795) ...

BlockWarps, WarpTile in Generic2dBlockShape are wave size dependent, it causes mangled name mismatch between host and device side.

Solution: Replace them with ThreadPerBlock and move BlockWarps, WarpTile calculation into Generic2dBlockShape

2025-09-10 08:29:20 +08:00

..

instances

Support Wave32 in CK_TILE - Part 1 (#2594)

2025-08-18 10:08:31 -07:00

CMakeLists.txt

[CK_Tile] Refactor Permute and MOE Smoothquant ctests to gtests (#2622)

2025-08-14 11:01:54 -07:00

moe_smoothquant.hpp

[CK_TILE] Refine Generic2dBlockShape to fix ck_tile example 2,10,11,14 on rdna3 and 4 (#2795)

2025-09-10 08:29:20 +08:00

test_moe_smoothquant_cases.inc

[CK_Tile] Refactor Permute and MOE Smoothquant ctests to gtests (#2622)

2025-08-14 11:01:54 -07:00

test_moe_smoothquant_types.hpp

[CK_Tile] Refactor Permute and MOE Smoothquant ctests to gtests (#2622)

2025-08-14 11:01:54 -07:00

test_moe_smoothquant_util.hpp

[CK_Tile] Refactor Permute and MOE Smoothquant ctests to gtests (#2622)

2025-08-14 11:01:54 -07:00

test_moe_smoothquant.cpp

[CK_Tile] Refactor Permute and MOE Smoothquant ctests to gtests (#2622)

2025-08-14 11:01:54 -07:00