Qianfeng Zhang fb496fa2d6 Add kQKHeaddimForGemmN and kVHeaddimForGemmN in order to support headdim 96

2024-10-12 13:27:02 +00:00

..

fmha_bwd_kernel.hpp

Add kQKHeaddimForGemmN and kVHeaddimForGemmN in order to support headdim 96

2024-10-12 13:27:02 +00:00

fmha_fwd_appendkv_kernel.hpp

[CK_TILE] Add PagedAttention kernels (#1387)

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

fmha_fwd_appendkv_tile_partitioner.hpp

[CK_TILE] Add PagedAttention kernels (#1387)

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

fmha_fwd_kernel.hpp

Adding seed and offset pointer support to the philox random number generator. (#1523)

2024-10-05 02:48:47 +08:00

fmha_fwd_splitkv_combine_kernel.hpp

[CK_TILE] Change output accum tensor layout of fmha fwd split-kv & combine kernels (#1527)

2024-10-01 22:13:52 +08:00

fmha_fwd_splitkv_combine_tile_partitioner.hpp

[CK_TILE] Change output accum tensor layout of fmha fwd split-kv & combine kernels (#1527)

2024-10-01 22:13:52 +08:00

fmha_fwd_splitkv_kernel.hpp

[CK_TILE] Change output accum tensor layout of fmha fwd split-kv & combine kernels (#1527)

2024-10-01 22:13:52 +08:00

fmha_fwd_splitkv_tile_partitioner.hpp

[CK_TILE] Change output accum tensor layout of fmha fwd split-kv & combine kernels (#1527)

2024-10-01 22:13:52 +08:00

fmha_fwd_tile_partitioner.hpp

CK Tile FA Training kernels (#1286)

2024-06-04 13:12:45 -05:00