mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-04 21:51:28 +00:00
* remove redundant kernels. * added batched_gemm_xdl_fp16int4_b_scale_v3 * Enabled the split K. * added the batched_gemm_b_scale ckProfiler, meet function issue * fix some typo * fix ckProfiler build issue * fix some bugs * updated some debug info * comment some code * Fix * fixed some bugs and refactor the code * fixed a function bug. * formatted files. * formatted * uncommented the ckProfiler CMakeLists * fixed. * fix ckProfiler for batched_gemm_b_scale --------- Co-authored-by: mtgu0705 <mtgu@amd.com> Co-authored-by: aska-0096 <haocwang@amd.com> Co-authored-by: Bartlomiej Kocot <barkocot@amd.com>
28 lines
1.4 KiB
CMake
28 lines
1.4 KiB
CMake
add_custom_target(example_batched_gemm_xdl)
|
|
|
|
add_example_executable(example_batched_gemm_xdl_fp32 batched_gemm_xdl_fp32.cpp)
|
|
add_example_dependencies(example_batched_gemm_xdl example_batched_gemm_xdl_fp32)
|
|
|
|
add_example_executable(example_batched_gemm_xdl_fp16 batched_gemm_xdl_fp16.cpp)
|
|
add_example_dependencies(example_batched_gemm_xdl example_batched_gemm_xdl_fp16)
|
|
|
|
add_example_executable(example_batched_gemm_xdl_bf16 batched_gemm_xdl_bf16.cpp)
|
|
add_example_dependencies(example_batched_gemm_xdl example_batched_gemm_xdl_bf16)
|
|
|
|
add_example_executable(example_batched_gemm_xdl_bf16_v3 batched_gemm_xdl_bf16_v3.cpp)
|
|
add_example_dependencies(example_batched_gemm_xdl example_batched_gemm_xdl_bf16_v3)
|
|
|
|
add_example_executable(example_batched_gemm_xdl_fp8_rowwise_v3 batched_gemm_xdl_fp8_rowwise_v3.cpp)
|
|
add_example_dependencies(example_batched_gemm_xdl example_batched_gemm_xdl_fp8_rowwise_v3)
|
|
|
|
add_example_executable(example_batched_gemm_xdl_int8 batched_gemm_xdl_int8.cpp)
|
|
add_example_dependencies(example_batched_gemm_xdl example_batched_gemm_xdl_int8)
|
|
|
|
if(USE_BITINT_EXTENSION_INT4)
|
|
add_example_executable(example_batched_gemm_xdl_int4 batched_gemm_xdl_int4.cpp)
|
|
add_example_dependencies(example_batched_gemm_xdl example_batched_gemm_xdl_int4)
|
|
endif()
|
|
|
|
add_example_executable(example_batched_gemm_xdl_fp16int4_b_scale_v3 batched_gemm_xdl_fp16int4_b_scale_v3.cpp)
|
|
add_example_dependencies(example_batched_gemm_xdl example_batched_gemm_xdl_fp16int4_b_scale_v3)
|