Adam Osewski 061ac0649c Polished Grouped GEMM APIs and new BF16 instances (#1600) ...

* Few small fixes.

* New GroupedGemm instances (BF16)

* Unify and refactor GroupedGEMM device API.

* Adapt changes to new API.

* Adapt grouped gemm profiler.

* Accept multiple kbatches for grouped gemm profiler.

- delete obsolete two stage as it is now covered by grouped gemm

* Update unit test for grouped gemm.

* Fix thresholds for BF16 and F8. Unblock tests.

* Fix few instances.

* Multiple small fixes.

* Adapt to new API, check dynamic casting.

* Uncomment few data types in grouped gemm profiler.

* Fix call to SetDeviceArgs.

* Fix profile grouped gemm multiply tile loop.

* Fix grouped gemm tile loop kernel args in client examples.

* Review comments.

2024-11-27 13:02:44 +01:00

..

CMakeLists.txt

ggemm tile_loop multD bf16 int8 (#1258)

2024-04-26 10:37:49 -05:00

grouped_gemm_bias_fastgelu_xdl_bf16_i8.cpp

bf16A_Int8B with fastgelu/bias (#1264)

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

grouped_gemm_fastgelu_xdl_bf16_i8.cpp

ggemm tile_loop multD bf16 int8 (#1258)

2024-04-26 10:37:49 -05:00

grouped_gemm_multiply_bias_fastgelu_xdl_bf16_i8.cpp

Polished Grouped GEMM APIs and new BF16 instances (#1600)

2024-11-27 13:02:44 +01:00

grouped_gemm_multiply_xdl_bf16_i8.cpp

Polished Grouped GEMM APIs and new BF16 instances (#1600)

2024-11-27 13:02:44 +01:00

grouped_gemm_xdl_bf16_i8.cpp

ggemm tile_loop multD bf16 int8 (#1258)

2024-04-26 10:37:49 -05:00