leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

v4.1 release update v2. (#2481)

Browse Source
This commit is contained in:
Junkai-Wu
2025-07-22 10:03:55 +08:00
committed by GitHub
parent 9baa06dd57
commit fd6cfe1ed0
179 changed files with 7878 additions and 1286 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/13_two_tensor_op_fusion/threadblock/b2b_mma_pipelined.h
View File

@@ -277,7 +277,7 @@ public:
IteratorAccumulatorScaleBias iterator_A1_scale, ///< iterator over A1 operand scale vectors in global memory
IteratorAccumulatorScaleBias iterator_A1_bias, ///< iterator over A1 operand bias vectors in global memory
IteratorB1 iterator_B1, ///< iterator over B1 operand in global memory
FragmentC0 const &src_accum, ///< source accumualtor tile
FragmentC0 const &src_accum, ///< source accumulator tile
OutputOp output_op_0, ///< epilogue operation after 1st Gemm
TransformA0 transform_A0 = TransformA0(), ///< transformation applied to A0 fragment
TransformB0 transform_B0 = TransformB0(), ///< transformation applied to B0 fragment

2
examples/13_two_tensor_op_fusion/threadblock/b2b_mma_pipelined_smem_accumulator.h
View File

@@ -298,7 +298,7 @@ public:
IteratorAccumulatorScaleBias iterator_accum0_scale, ///< iterator over D0 scale vector in global memory
IteratorAccumulatorScaleBias iterator_accum0_bias, ///< iterator over D0 bias vector in global memory
IteratorB1 iterator_B1, ///< iterator over B1 operand in global memory
FragmentC0 const &src_accum, ///< source accumualtor tile
FragmentC0 const &src_accum, ///< source accumulator tile
OutputOp output_op_0, ///< epilogue operation after 1st Gemm
TransformA0 transform_A0 = TransformA0(), ///< transformation applied to A0 fragment
TransformB0 transform_B0 = TransformB0(), ///< transformation applied to B0 fragment

2
examples/13_two_tensor_op_fusion/threadblock/default_b2b_mma.h
View File

@@ -93,7 +93,7 @@ template <
typename InstructionShape_,
/// Number of stages used in the pipelined mainloop
int Stages,
/// Operation perfomed by GEMM
/// Operation performed by GEMM
typename Operator,
/// Epilogue output operator
typename EpilogueOutputOp,