cutlass

leavelet/cutlass

Fork 0

Files

T

History

64579189ec Feature/add bottom causal mask (#2480 )

* Rebase to latest

* update

* upd

Summary:

Test Plan:

Reviewers:

Subscribers:

Tasks:

Tags:

* Update fmha_fusion.hpp

* Update fmha_fusion.hpp

fixed flipped logic for isQBegin

* Update fmha_fusion.hpp

* Avoid use of booleans

The current expression is confusing

* fmt

* Update fmha_fusion.hpp

Reproduce error/fix with: 
./77_blackwell_fmha_fp16 --verify --b=1 --q=1013 --k=1024 --h=1 --h_k=1 --mask=causal --causal-type=qend

* add test, format

---------

Co-authored-by: Richard Cai <ricai@nvidia.com>
Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>

2025-09-18 17:11:23 -04:00

fmha_common.hpp

CUTLASS 3.8 Release (#2059 )

2025-01-25 02:44:06 -05:00

fmha_fusion.hpp

Feature/add bottom causal mask (#2480 )

2025-09-18 17:11:23 -04:00

sm100_fmha_fwd_epilogue_tma_warpspecialized.hpp

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

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

sm100_fmha_fwd_mainloop_tma_warpspecialized.hpp

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