Qianfeng 8632221814 [CK_TILE] Add fmha fwd headdim96 support (#1608) ...

* Add ceil_to_qualified_tile_length()

* Rename kK0BlockLength to kQKHeaddim

* Add kSubQKHeaddim concept to support headdim96

* Fix in math.hpp to avoid using __half interfaces

* Add LdsBufferSequence instance for headdim96

* Update in fmha_fwd/fmha_fwd_splitkv codegen to support hd96 testing

* Disable hd96 instance generation in codegen fmha_fwd and fmha_fwd_splitkv to save compiling time

* Reformat one file

* Fix text alignment in fmha_fwd_splitkv.py

---------

Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>

2024-10-30 14:03:16 +08:00

..

__init__.py

[CK_TILE] fmha forward split-kv + combine kernels (#1338)

2024-06-26 17:41:15 +08:00

fmha_bwd.py

[CK_TILE] FA bwd kernels optimization (#1397)

2024-08-16 13:40:10 -07:00

fmha_fwd_appendkv.py

[CK_TILE] Add PagedAttention kernels (#1387)

2024-08-28 20:50:43 +08:00

fmha_fwd_splitkv.py

[CK_TILE] Add fmha fwd headdim96 support (#1608)

2024-10-30 14:03:16 +08:00

fmha_fwd.py

[CK_TILE] Add fmha fwd headdim96 support (#1608)

2024-10-30 14:03:16 +08:00