leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
d4be5ab5d7d926ae171a3724a473f83435efdda9
cutlass/include/cutlass/gemm/kernel
History
Aleksandar Samardžić 5c756eb774 Add support for sparse GEMM with visitor epilogue (#1189) 
* Add support for sparse GEMM with visitor epilogue

* Refactor changes at the kernel level
2024-01-04 12:38:11 -05:00
..
default_ell_gemm.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_gemm_complex.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_gemm_grouped_softmax_mainloop_fusion.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_gemm_grouped.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_gemm_layernorm_mainloop_fusion.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_gemm_planar_complex_universal.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_gemm_sparse_row_broadcast.h
Add support for sparse GEMM with row broadcasted bias vector (#951)
2023-05-24 10:25:05 -04:00
default_gemm_sparse_with_visitor.h
Add support for sparse GEMM with visitor epilogue (#1189)
2024-01-04 12:38:11 -05:00
default_gemm_sparse.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_gemm_splitk_parallel.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_gemm_streamk_with_broadcast.h
Stream-K with broadcast (#892)
2023-05-22 19:05:06 -04:00
default_gemm_universal_with_visitor.h
CUTLASS 3.2.1 (#1113)
2023-09-26 17:24:26 -04:00
default_gemm_universal.h
[doc] fix: fix typos in the comment (#1049)
2023-08-16 11:39:25 -04:00
default_gemm_with_broadcast.h
CUTLASS 3.1 (#915)
2023-04-14 23:19:34 -04:00
default_gemm_with_k_reduction.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_gemm_with_reduction.h
CUTLASS 3.1 (#915)
2023-04-14 23:19:34 -04:00
default_gemm.h
CUTLASS 3.1 (#915)
2023-04-14 23:19:34 -04:00
default_gemv.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_rank_2k_complex.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_rank_2k_grouped.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_rank_2k_universal.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_rank_2k.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_rank_k_complex.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_rank_k_universal.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_rank_k.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_symm_complex.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_symm_universal.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_symm.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_trmm_complex.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_trmm_universal.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
default_trmm.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
ell_gemm.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
gemm_array.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
gemm_batched.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
gemm_grouped_problem_visitor.h
CUTLASS 3.2.1 (#1113)
2023-09-26 17:24:26 -04:00
gemm_grouped_softmax_mainloop_fusion.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
gemm_grouped.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
gemm_layernorm_mainloop_fusion.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
gemm_params.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
gemm_pipelined.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
gemm_planar_complex_array.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
gemm_planar_complex.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
gemm_splitk_parallel.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
gemm_streamk_with_fused_epilogue.h
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
gemm_transpose_operands.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
gemm_universal_streamk.h
Collection of changes to fix clang build. (#1200)
2023-12-08 14:42:12 -05:00
gemm_universal_with_visitor_streamk.h
CUTLASS 3.3.0 (#1167)
2023-11-02 11:09:05 -04:00
gemm_universal_with_visitor.h
CUTLASS 3.2.1 (#1113)
2023-09-26 17:24:26 -04:00
gemm_universal.h
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
gemm_universal.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
gemm_with_fused_epilogue.h
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
gemm_with_k_reduction.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
gemm.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
gemv_batched_strided.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
gemv.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
grouped_problem_visitor.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
params_sparse_base.h
Add support for sparse GEMM with visitor epilogue (#1189)
2024-01-04 12:38:11 -05:00
params_universal_base.h
CUTLASS 3.2.1 (#1113)
2023-09-26 17:24:26 -04:00
rank_2k_grouped_problem_visitor.h
CUTLASS 3.1 (#915)
2023-04-14 23:19:34 -04:00
rank_2k_grouped.h
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
rank_2k_transpose_operands.h
New updates for 2.11 (#775)
2023-01-20 16:32:57 -05:00
rank_2k_universal.h
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
rank_k_universal.h
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sm70_gemm.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sm90_gemm_array_tma_warpspecialized_cooperative.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sm90_gemm_tma_warpspecialized_cooperative.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sm90_gemm_tma_warpspecialized_pingpong.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sm90_gemm_tma_warpspecialized.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sm90_gemm_tma.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sm90_gemm_warpspecialized_cooperative.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sm90_gemm_warpspecialized_pingpong.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sm90_gemm_warpspecialized.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sm90_tile_scheduler_group.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sm90_tile_scheduler_stream_k.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sm90_tile_scheduler.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
sparse_gemm_row_broadcast.h
Add support for sparse GEMM with row broadcasted bias vector (#951)
2023-05-24 10:25:05 -04:00
sparse_gemm_with_visitor.h
Add support for sparse GEMM with visitor epilogue (#1189)
2024-01-04 12:38:11 -05:00
sparse_gemm.h
Add support for sparse GEMM with visitor epilogue (#1189)
2024-01-04 12:38:11 -05:00
symm_universal.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00
tile_scheduler_params.h
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
tile_scheduler.hpp
CUTLASS 3.4.0 (#1286)
2023-12-29 15:21:31 -05:00
trmm_universal.h
CUTLASS 3.2 (#1024)
2023-08-07 20:50:32 -04:00