mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-15 10:37:44 +00:00
f6d2ca82b7
* add sparse attention VSA
* fix the pre-commit
* Add jenga test and pre-commit
* add bf16 for vsa
* add jenga support bf16
* remove lse arg
* split kernel code to block & kernel
* fix the pre-commit
* fix the pre-commit
* fix the copyrights
* fix the copyright
* fix the copyright & rename block to pipeline
* fix the copyright and pipeline
* remove lse & dropout & add fmt
* fix the jenga&VSA code review
* remove the useless code & resolved the comments
* remove useless code
* remove useless code
* Clean up code
* Remove more unused code
* Re-format .hpp
* Refactor codegen scripts
---------
Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>
Co-authored-by: asleepzzz <hanwen.chang@amd.com>
[ROCm/composable_kernel commit: 4d2f8c111e]
35 lines
1022 B
CMake
35 lines
1022 B
CMake
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
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(40_streamk_gemm)
|
|
add_subdirectory(41_batched_contraction)
|
|
add_subdirectory(50_sparse_attn)
|
|
|