mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-05 06:01:23 +00:00
76696ace44
* update grouped_gemm blockwise kernel * update config * update kernel * update examples * remove test code for now * sync test files with origin/develop * update example * fix code lint * fix code-lint * update test code * run clang format * run pre-commit * update api
43 lines
1.3 KiB
CMake
43 lines
1.3 KiB
CMake
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
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(grouped_gemm_quant)
|
|
add_subdirectory(grouped_gemm_abquant)
|
|
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(warp_gemm)
|
|
add_subdirectory(reduce)
|
|
add_subdirectory(core)
|
|
add_subdirectory(epilogue)
|
|
add_subdirectory(atomic_add_op)
|
|
add_subdirectory(fmha)
|
|
add_subdirectory(gemm_tile_engine)
|
|
add_subdirectory(pooling)
|
|
add_subdirectory(grouped_conv)
|