mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-02 12:41:26 +00:00
a44bea45b2
* feat(grouped_gemm_multi_d): add new example that integrates grouped_gemm and multi_d_gemm feature * feat: generalized grouped_gemm_kernel.hpp * feat: generalized grouped_gemm_kernel.hpp even further by removing hardcoded 0 * refactor: grouped_gemm_multi_d relies on grouped_gemm_kernel * tests(grouped_gemm): grouped_gemm test suite passes with minor adjustments * fix: segfault fix by passing correct parameters for d tensors * docs: add multi d info and trim down outdated content * tests: add unit tests for grouped_gemm_multi_d and minor changes in grouped_gemm related test for compatibility * style: clang format * fix: incorrect validation method and Dtensor layout in test suite
33 lines
1.0 KiB
CMake
33 lines
1.0 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)
|