mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 18:17:44 +00:00
* comment on specialization for TensorSpecialization::Packed
* gemm_softmax_gemm with output permutation
* scaling
* refactor MatrixPadder; rename to GemmPadder
* remove old sanity check
* restore original gemm_softmax_gemm
* revise comment in gemm_softmax_gemm example
* use GetElementSpaceSize()
* remove extra header
* typo
* remove archaic DeviceOpPtr
[ROCm/composable_kernel commit: e0d8806ca1]