aska-0096 c69d450b22 bm0=32 not correct, support hdim48, performance not good

2025-07-11 06:55:02 +00:00

..

bit_cast.hpp

introducing ck_tile! (#1216)

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

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

bm0=32 not correct, support hdim48, performance not good

2025-07-11 06:55:02 +00:00

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] FA bwd kernels optimization (#1397)

2024-08-16 13:40:10 -07:00

random.hpp

introducing ck_tile! (#1216)

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

reduce_operator.hpp

[Ck tile] support rmsnorm and related fusion (#1605)

2024-10-30 15:22:56 +08:00

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 GEMM Compute V2 (2 LDS Ping Pong mechanism) (#1853)

2025-02-12 14:33:09 -08:00

type_traits.hpp

[CK_TILE] Tileloop persistent gemm - resubmit (#2299)

2025-06-06 14:18:49 -07:00

unary_element_function.hpp

add fp8 as dst (#1830)

2025-01-22 17:34:27 +08:00