mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 05:01:25 +00:00
7b6451b68e
* Pooling 2D/3D with refernce * Tests & cleanup - added test for ppoling - cleanup - removed 2d example * Comment resolution - README added - example target name rectified - appropriate arg description and comments added * clang-format * appropriate blocksize calc * modifications for future indexing addition - instead of transforming views we now transform the descriptors, so that the same descriptor can be re-used for index tensor in the future * some basic fixes * comment resolutions * comment resolutions --------- Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
35 lines
1.1 KiB
CMake
35 lines
1.1 KiB
CMake
add_subdirectory(image_to_column)
|
|
add_subdirectory(gemm)
|
|
add_subdirectory(gemm_weight_preshuffle)
|
|
add_subdirectory(batched_gemm)
|
|
add_subdirectory(grouped_gemm)
|
|
add_subdirectory(grouped_gemm_preshuffle)
|
|
add_subdirectory(grouped_gemm_multi_d)
|
|
add_subdirectory(gemm_multi_d)
|
|
add_subdirectory(gemm_multi_abd)
|
|
add_subdirectory(gemm_streamk)
|
|
add_subdirectory(data_type)
|
|
add_subdirectory(container)
|
|
add_subdirectory(elementwise)
|
|
# Not including these tests as there is a bug on gfx90a and gfx942
|
|
# resulting in "GPU core dump"
|
|
#add_subdirectory(moe_smoothquant)
|
|
add_subdirectory(permute)
|
|
add_subdirectory(moe_sorting)
|
|
add_subdirectory(slice_tile)
|
|
add_subdirectory(memory_copy)
|
|
add_subdirectory(batched_transpose)
|
|
add_subdirectory(smoothquant)
|
|
add_subdirectory(topk_softmax)
|
|
add_subdirectory(add_rmsnorm2d_rdquant)
|
|
# add_subdirectory(layernorm2d)
|
|
# add_subdirectory(rmsnorm2d)
|
|
add_subdirectory(gemm_block_scale)
|
|
add_subdirectory(utility)
|
|
add_subdirectory(reduce)
|
|
add_subdirectory(epilogue)
|
|
add_subdirectory(atomic_add_op)
|
|
add_subdirectory(fmha)
|
|
add_subdirectory(gemm_tile_engine)
|
|
add_subdirectory(pooling)
|