carlushuang 353a612b44 [CK_TILE] add moe-sorting MP kernel (#1910) ...

* moe sorting ex

* fix bug for race condition

* fix bug and optimze large expert

* fix

* optimize with sub_token_oneshot

* support skip empty tokens for expert sorting

* update moe_sorting

* tidy code

* support mp kernel

* hint mp

* remove use less code

* porting to example 15

---------

Co-authored-by: valarLip <340077269@qq.com>

2025-02-25 17:56:55 +08:00

..

add_rmsnorm2d_rdquant

[A8W8 GEMM] Optimized weight-preshuffled implementation & add quantization datatype for CK TILE rms_norm (#1862)

2025-02-20 14:00:27 -08:00

batched_transpose

add batched_transpose implement (#1660)

2025-01-28 16:22:02 -08:00

common

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

elementwise

[CK TILE] GEMM with packed i4 (#1885)

2025-02-20 09:59:49 +01:00

epilogue

Support for dtypes (fp8, bf8, bf16 and fp16) for the ck_tile/03_gemm example. (#1845)

2025-02-07 15:07:06 -07:00

flatmm/block

Merge from internal (#1857)

2025-02-07 15:05:05 -07:00

fmha

Ck tile/paged attention workaround (#1894)

2025-02-17 14:29:25 +08:00

fused_moe

[CK_TILE] add moe-sorting MP kernel (#1910)

2025-02-25 17:56:55 +08:00

gemm

[CK TILE] GEMM with packed i4 (#1885)

2025-02-20 09:59:49 +01:00

image_to_column

[CK_TILE] Image to Column kernel (#1532)

2024-09-27 22:57:38 +02:00

layernorm2d

[CK_TILE] Add Various Fusion Functions to RMSNorm (#1802)

2025-01-15 10:23:48 +08:00

norm_reduce

Ck tile/layernorm: implement naive reduce, opt performance (#1784)

2025-01-03 14:28:59 +08:00

permute

Remove virtual destructors from unary ops (#1610)

2024-10-30 17:42:50 +01:00

reduce/block

[Ck_tile] smoothquant (#1617)

2024-11-01 13:51:56 +08:00

rmsnorm2d

[CK_TILE] Add Various Fusion Functions to RMSNorm (#1802)

2025-01-15 10:23:48 +08:00

smoothquant

add fp8 as dst (#1830)

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

softmax/block

topk_softmax (#1592)

2024-10-26 23:52:49 +08:00

topk/block

topk_softmax (#1592)

2024-10-26 23:52:49 +08:00

topk_softmax

topk_softmax (#1592)

2024-10-26 23:52:49 +08:00

add_rmsnorm2d_rdquant.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

batched_transpose.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

common.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

elementwise.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

epilogue.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

flatmm.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

fmha.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

fused_moe.hpp

[CK_TILE] moe sorting ex kernel to support expert > 128 (#1840)

2025-02-11 17:49:17 +08:00

gemm.hpp

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

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

image_to_column.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

layernorm2d.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

norm_reduce.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

permute.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

reduce.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

rmsnorm2d.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

smoothquant.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

softmax.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

topk_softmax.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00

topk.hpp

[CK_TILE] Add GetName for GEMM kernels (#1791)

2025-02-11 09:49:48 +01:00