mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-04 13:41:24 +00:00
- Added support for static_distributed_tensor<...> - Added support for tile_distribution<...> - Added support for tensor_view<...> - Added support for tensor_descriptor<...> Now type-print handles both: 1. Type aliases (::BottomTensorView, ::TensorDesc, etc.) 2. Full types with no runtime storage (static_distributed_tensor, etc.) Shows [from type] indicator for all type-only extractions. Example: type-print dst_tensor Works even when 'p dst_tensor' shows 'Cannot access memory' Co-Authored-By: Claude <noreply@anthropic.com>
33 lines
951 B
CMake
33 lines
951 B
CMake
include_directories(AFTER
|
|
${CMAKE_CURRENT_LIST_DIR}
|
|
)
|
|
|
|
add_subdirectory(01_fmha)
|
|
add_subdirectory(02_layernorm2d)
|
|
add_subdirectory(03_gemm)
|
|
add_subdirectory(04_img2col)
|
|
add_subdirectory(05_reduce)
|
|
add_subdirectory(06_permute)
|
|
add_subdirectory(09_topk_softmax)
|
|
add_subdirectory(10_rmsnorm2d)
|
|
add_subdirectory(11_add_rmsnorm2d_rdquant)
|
|
add_subdirectory(12_smoothquant)
|
|
add_subdirectory(13_moe_sorting)
|
|
add_subdirectory(14_moe_smoothquant)
|
|
add_subdirectory(15_fused_moe)
|
|
add_subdirectory(16_batched_gemm)
|
|
add_subdirectory(17_grouped_gemm)
|
|
add_subdirectory(18_flatmm)
|
|
add_subdirectory(19_gemm_multi_d)
|
|
add_subdirectory(20_grouped_convolution)
|
|
add_subdirectory(21_elementwise)
|
|
add_subdirectory(22_gemm_multi_abd)
|
|
add_subdirectory(35_batched_transpose)
|
|
add_subdirectory(36_pooling)
|
|
add_subdirectory(38_block_scale_gemm)
|
|
add_subdirectory(39_copy)
|
|
add_subdirectory(40_streamk_gemm)
|
|
add_subdirectory(41_batched_contraction)
|
|
add_subdirectory(99_toy_example)
|
|
|