Skip to content

Cutlass APIs changes for Fusion Epilogue #657

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
rishi-yadav wants to merge 2 commits into
base: main
Choose a base branch
from
+1,663 −1
Open

Cutlass APIs changes for Fusion Epilogue #657

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b311371
Cutlass APIs changes for Fusionwq
rishi-yadav Dec 4, 2025
3ab70cc
Softmax tests are failing
rishi-yadav Dec 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion include/cutlass/epilogue/fusion/xe_visitor_splitk.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,7 +192,7 @@ struct XeSplitK
visit(Array<ElementAccumulator, FragmentSize> const& frg_acc, int epi_v, int epi_m, int epi_n,
Array<ElementInput, FragmentSize> const& frg_input) {

return frg_acc;
return frg_input;
}

template<class STensor, class SyncFn, class VTensor>
Expand Down
3 changes: 3 additions & 0 deletions test/unit/gemm/device/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,9 @@ if(CUTLASS_ENABLE_SYCL)
cutlass_test_unit_add_executable(
cutlass_test_unit_gemm_device_tensorop_epilogue_fusion_xe
xe_gemm_bf16_bf16_fp32_tensor_op_fp32_evt.cpp
xe_gemm_bf16_bf16_fp32_lincombtopksoftmaxcol_tensor_op_f32.cpp
xe_gemm_bf16_bf16_fp32_lincomb_splitk_tensor_op_f32.cpp
# xe_gemm_bf16_bf16_fp32_lincomb_softmaxrow_tensor_op_f32.cpp
)

cutlass_test_unit_add_executable(
Expand Down
Loading
Loading