Junkai-Wu 6a35b4d22f v4.2 tag release. (#2638)

2025-09-15 12:21:53 -04:00

..

fmha_causal_tile_scheduler.hpp

Add Blackwell MLA forward (shape: d=192, dv=128) implementation in example_77 (#2472)

2025-07-18 01:27:48 -04:00

fmha_kernel_bwd_convert.hpp

ex77 backwards GQA (#2556)

2025-09-09 12:53:28 -04:00

fmha_kernel_bwd_sum_OdO.hpp

ex77 backwards GQA (#2556)

2025-09-09 12:53:28 -04:00

fmha_options.hpp

Revert "[ex77] fix mla split; add fwd lse; add bwd varlen (#2366)" (#2370)

2025-06-05 23:14:57 -04:00

fmha_tile_scheduler.hpp

Revert "[ex77] fix mla split; add fwd lse; add bwd varlen (#2366)" (#2370)

2025-06-05 23:14:57 -04:00

sm100_fmha_bwd_kernel_tma_warpspecialized.hpp

v4.2 tag release. (#2638)

2025-09-15 12:21:53 -04:00

sm100_fmha_bwd_mla_kernel_tma_warpspecialized.hpp

v4.2 tag release. (#2638)

2025-09-15 12:21:53 -04:00

sm100_fmha_fwd_kernel_tma_warpspecialized.hpp

v4.2 tag release. (#2638)

2025-09-15 12:21:53 -04:00

sm100_fmha_gen_kernel_warpspecialized.hpp

v4.2 tag release. (#2638)

2025-09-15 12:21:53 -04:00

sm100_fmha_mla_reduction.hpp

Example 77 add blackwell fmha bwd for MLA shape (#2466)

2025-07-24 18:41:11 -04:00

sm100_fmha_mla_tma_warpspecialized.hpp

v4.2 tag release. (#2638)

2025-09-15 12:21:53 -04:00

sm100_mla_tile_scheduler.hpp

Example 77 add blackwell fmha bwd for MLA shape (#2466)

2025-07-24 18:41:11 -04:00