ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-17 11:30:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '7795e73b47a34a25b48a14f3e4e0e6d681fcbde5' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-12-19 05:14:28 +00:00
parent 9073821d40
commit 0779609ddc
13 changed files with 1788 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1456
include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_wmma_cshuffle_v3_large_tensor.hpp Normal file
View File

File diff suppressed because it is too large Load Diff

2
include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_large_tensor_cshuffle.hpp
View File

@@ -327,7 +327,7 @@ struct DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor
Array<const ADataType*, MaxGemmsNum> a_grid_ptrs_arr;
Array<DsPointer, MaxGemmsNum> ds_grid_ptrs_arr;
Array<EDataType*, MaxGemmsNum> c_grid_ptrs_arr;
// Queue for spliting
// Queue for splitting
std::queue<ConvToGemmFwdTransformerLongIndexT> conv_to_gemm_transformers_queue(
{conv_to_gemm_transformer_base});
std::queue<const ADataType*> a_grid_ptrs_queue({a_grid_ptr_base});