ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-20 21:09:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '88ae4455806efe2019bb0403606f7c4a1e3d9c3a' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-12-29 12:22:38 +00:00
parent c3c8c20144
commit 0b6dde06c3
10 changed files with 47 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_multiple_d_wmma_cshuffle_v3.hpp
View File

@@ -746,7 +746,6 @@ struct DeviceGroupedConvBwdWeightMultipleD_Wmma_CShuffleV3
arg.a_grid_desc_kbatch_k0_m_k1_.GetLength(I2);
AccDataType* p_e_grid = type_convert<AccDataType*>(arg.p_workspace_);
;
// Convolution kernel dispatch
typename GridwiseGemm::Argument gemm_arg{

4
include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
View File

@@ -348,9 +348,7 @@ struct Bilinear
__host__ __device__ constexpr void
operator()<bhalf_t, float, bhalf_t>(bhalf_t& y, const float& x0, const bhalf_t& x1) const
{
const float x1_tmp = ck::type_convert<float>(x1);
const float y_tmp = alpha_ * x0 + beta_ * x1_tmp;
y = y_tmp;
y = type_convert<bhalf_t>(alpha_ * x0 + beta_ * ck::type_convert<float>(x1));
};
template <>