feli 3786e16375 ck moe gemm implement (#1936) ...

* port all moe changes from ck_moe_gemm branch

* refine codes in the pr

* fix tail odd

* fix clang format

* fix clang format2

* make hot loop scheduler compatible with 16x16 and 32x32

* clang format

* fix per token quant

* rename moe example

* clang format

---------

Co-authored-by: coderfeli <coderfeli@163.com>

2025-03-05 15:56:55 +08:00

..

reduction_functions_threadwise.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

threadwise_contraction_dl.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

threadwise_gemm_dlops_v3.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

threadwise_tensor_slice_set.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

threadwise_tensor_slice_transfer_util.hpp

Added Multi_ABD support into Gemm and GroupedGemmFixedNK (#978)

2024-04-15 21:09:45 -05:00

threadwise_tensor_slice_transfer_v3r1_dequant.hpp

Navi3 rel (#1176)

2024-03-08 17:11:51 -08:00

threadwise_tensor_slice_transfer_v3r1_gather.hpp

ck moe gemm implement (#1936)

2025-03-05 15:56:55 +08:00

threadwise_tensor_slice_transfer_v3r1.hpp

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

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

threadwise_tensor_slice_transfer_v3r2.hpp

Add elementwise with dynamic vector dim (#1198)

2024-03-22 10:40:43 +01:00

threadwise_tensor_slice_transfer_v4r1.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

threadwise_tensor_slice_transfer_v5r1.hpp

Moficiation to fix this issue "threadwise_tensor_slice_transfer_v5r1 issue #1279" (#1492)

2024-09-04 21:52:55 -07:00

threadwise_tensor_slice_transfer_v6r1.hpp

add an example of customized type convert - bfp16_rtn (#869)

2023-08-29 12:31:24 -05:00

threadwise_tensor_slice_transfer_v6r1r2.hpp

initial stream-k implementation with example (#699)

2023-07-26 14:18:15 -05:00

threadwise_tensor_slice_transfer_v6r2.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

threadwise_tensor_slice_transfer_v6r3.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

threadwise_tensor_slice_transfer_v7.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

threadwise_tensor_slice_transfer_v7r2.hpp

bf16A_Int8B with fastgelu/bias (#1264)

2024-04-26 07:26:30 -05:00

threadwise_tensor_slice_transfer_v7r3_scatter.hpp

ck moe gemm implement (#1936)

2025-03-05 15:56:55 +08:00

threadwise_tensor_slice_transfer_v7r3.hpp

add f8 gemm multiD with both row/col wise scale (#1300)

2024-05-28 12:04:22 -05:00

threadwise_tensor_slice_transfer.hpp

Codegen hipRTC compilation (#1579)

2025-01-31 09:48:39 -08:00

threadwise_welford.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00