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

..

algorithm.hpp

move utility headers from library/include to include path (#1697)

2024-11-27 06:12:56 -08:00

check_err.hpp

Merge from internal (#1857)

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

conv_common.hpp

move utility headers from library/include to include path (#1697)

2024-11-27 06:12:56 -08:00

convolution_host_tensor_descriptor_helper.hpp

move utility headers from library/include to include path (#1697)

2024-11-27 06:12:56 -08:00

convolution_parameter.hpp

move utility headers from library/include to include path (#1697)

2024-11-27 06:12:56 -08:00

device_memory.hpp

move utility headers from library/include to include path (#1697)

2024-11-27 06:12:56 -08:00

fill.hpp

move utility headers from library/include to include path (#1697)

2024-11-27 06:12:56 -08:00

host_common_util.hpp

move utility headers from library/include to include path (#1697)

2024-11-27 06:12:56 -08:00

host_gemm.hpp

move utility headers from library/include to include path (#1697)

2024-11-27 06:12:56 -08:00

host_tensor_generator.hpp

Merge from internal (#1857)

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

host_tensor.hpp

ck moe gemm implement (#1936)

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

iterator.hpp

move utility headers from library/include to include path (#1697)

2024-11-27 06:12:56 -08:00

literals.hpp

move utility headers from library/include to include path (#1697)

2024-11-27 06:12:56 -08:00

numeric.hpp

move utility headers from library/include to include path (#1697)

2024-11-27 06:12:56 -08:00

ranges.hpp

move utility headers from library/include to include path (#1697)

2024-11-27 06:12:56 -08:00