mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-19 20:40:07 +00:00
ce0feff1af
* test(grouped_gemm): add gtests for the example to maintain its integrity
* test(grouped_gemm_preshuffle): add prefill variant to testbed to cover wider range
* fix: removed residue code to make b_shuffle() work again
* test(grouped_gemm_preshuffle): limit the test suite to gfx942 arch as it fails on gfx90a
* build: add gfx950 as build target for gtests
* test(grouped_gemm_preshuffle): temporarily disable fp8 prec tests due to numerical errors
* fix(grouped_gemm_preshuffle): resolved fp8 tests failure on gfx950 by adding correct compiler flag
[ROCm/composable_kernel commit: 48e08c6429]
31 lines
965 B
CMake
31 lines
965 B
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(gemm_multi_d)
|
|
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)
|