Max Podkorytov 2570462ecf [CK_TILE] Fix transpose_vectors for 2x2 8-bit tiles (#3042) ...

fix transpose_vectors logic for 2x2 8-bit tiles

    add a test which goes through this code path.

    factor out constexpr'd cases into smaller functions.

    add inline docs about the data movement

    impact: gemms with 8-bit non-rcr inputs on gfx942

2025-10-20 13:40:44 -07:00

..

bit_cast.hpp

introducing ck_tile! (#1216)

2024-04-15 19:27:12 -05:00

debug.hpp

[Util] add a RAII stuct which inserts markers into generated asm (#2748)

2025-09-08 22:02:02 -07:00

env.hpp

Split env.hpp header from the ck.hpp header. (#2049)

2025-04-03 15:30:21 -07:00

functional_with_tuple.hpp

update layernorm (#1570)

2024-10-22 09:26:18 +08:00

functional.hpp

add a fast compilation path for static for (0..N) (#2005)

2025-04-01 12:06:25 -07:00

ignore.hpp

introducing ck_tile! (#1216)

2024-04-15 19:27:12 -05:00

literals.hpp

[CK-Tile] Universal gemm memory bound pipeline (#1558)

2024-10-30 10:05:15 +01:00

magic_div.hpp

Fix Windows build. (#2012)

2025-04-01 12:22:10 -07:00

philox_rand.hpp

[CK_TILE] Support f32 in FMHA (fwd and bwd) (#2836)

2025-09-27 18:03:48 +05:00

print.hpp

[CK_TILE] Enable printing more structures in CK-Tile (#2443)

2025-08-07 15:45:27 +03:00

random.hpp

Fix UB caused by reinterpret_cast (#2849)

2025-09-18 07:12:37 -07:00

reduce_operator.hpp

fix identity values in Max and AbsMax (#3048)

2025-10-17 09:49:21 -07:00

static_counter.hpp

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

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

to_sequence.hpp

introducing ck_tile! (#1216)

2024-04-15 19:27:12 -05:00

transpose_vectors.hpp

[CK_TILE] Fix transpose_vectors for 2x2 8-bit tiles (#3042)

2025-10-20 13:40:44 -07:00

type_traits.hpp

upgrade from clang-format-12 to clang-format-18 (#2568)

2025-07-28 11:34:07 -07:00

unary_element_function.hpp

upgrade from clang-format-12 to clang-format-18 (#2568)

2025-07-28 11:34:07 -07:00