* Remove some duplicate code in fmha_fwd_appendkv_kernel.hpp

* Simplify two templated operator calls by having the templated types deduced automatically

* Simplify two GemmPipeline calls

* Fix GemmPipelineAgBgCrCompV4::GetName

* Refactor use of ArgParser in CK tile GEMM examples

* Update args in README.md to match the implementation in create_args

* Remove some unnecessary include statements

* Rename two variables

* Factor out common code

* Factor out do_verify

* Add and use type aliases for memory operation integral constants

* In gemm_basic.cpp, use kPadM, kPadN, kPadK, and kBlockPerCu from GemmConfig

---------

Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
This commit is contained in:
SamiAario-AMD
2025-08-13 11:12:08 +03:00
committed by GitHub
parent 05a6e92705
commit 28a97865f5
9 changed files with 142 additions and 178 deletions

View File

@@ -149,7 +149,7 @@ struct GemmPipelineAgBgCrCompV4 : public BaseGemmPipelineAgBgCrCompV4<Problem>
[[nodiscard]] CK_TILE_HOST static const std::string GetName()
{
// clang-format off
return concat('_', "pipeline_AgBgCrCompV3",
return concat('_', "pipeline_AgBgCrCompV4",
concat('x', MPerBlock, NPerBlock, KPerBlock, BlockSize),
concat('x', GetVectorSizeA(), GetVectorSizeB(), GetVectorSizeC()),
concat('x', kPadM, kPadN, kPadK));