mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 21:21:22 +00:00
b4032629e5
* Overload output stream operator for LoopScheduler and PiplineVersion * Add Run overload accepting grid descriptors MK. * Add __device__ keyword for CalculateGridSize * Create device op GroupedGemmMultipleD * Add GroupedGemm MultipleD Tile Loop implementation. * Add an example for GroupedGemm MultipleD tile loop. * Device Op GroupedGEMMTileLoop. * Bunch of small changes in exmaple. * CkProfiler * Remove unused tparam. * Fix include statement. * Fix output stream overloads. * Do not make descriptors and check validity untill we find group. * Fix gemm desc initialization. * Revert device op * Fix compilation for DTYPES=FP16 * Validate tensor transfers paramters. * Validate on host only NK dims if M is not known. * Fix bug. * A convenient debug func for selecting threads. * Fix has main k block loop bug. * Make sure that b2c has up to date tile offset. * Output stream operator for Sequence type. * Cmake file formatting.
36 lines
2.0 KiB
CMake
36 lines
2.0 KiB
CMake
add_custom_target(example_grouped_gemm_xdl)
|
|
add_example_executable(example_grouped_gemm_xdl_fp32 grouped_gemm_xdl_fp32.cpp)
|
|
add_example_dependencies(example_grouped_gemm_xdl example_grouped_gemm_xdl_fp32)
|
|
|
|
add_example_executable(example_grouped_gemm_xdl_fp16 grouped_gemm_xdl_fp16.cpp)
|
|
add_example_dependencies(example_grouped_gemm_xdl example_grouped_gemm_xdl_fp16)
|
|
|
|
add_example_executable(example_grouped_gemm_multiple_d_dl_fp16 grouped_gemm_multiple_d_dl_fp16.cpp)
|
|
add_example_dependencies(example_grouped_gemm_xdl example_grouped_gemm_multiple_d_dl_fp16)
|
|
|
|
add_example_executable(example_grouped_gemm_xdl_splitk_fp16 grouped_gemm_xdl_splitk_fp16.cpp)
|
|
add_example_dependencies(example_grouped_gemm_xdl example_grouped_gemm_xdl_splitk_fp16)
|
|
|
|
add_example_executable(example_grouped_gemm_xdl_fixed_nk_fp16 grouped_gemm_xdl_fixed_nk_fp16.cpp)
|
|
add_example_dependencies(example_grouped_gemm_xdl example_grouped_gemm_xdl_fixed_nk_fp16)
|
|
|
|
add_example_executable(example_grouped_gemm_xdl_fixed_nk_bias_fp16 grouped_gemm_xdl_fixed_nk_bias_fp16.cpp)
|
|
add_example_dependencies(example_grouped_gemm_xdl example_grouped_gemm_xdl_fixed_nk_bias_fp16)
|
|
|
|
add_example_executable(example_grouped_gemm_xdl_bf16 grouped_gemm_xdl_bf16.cpp)
|
|
add_example_dependencies(example_grouped_gemm_xdl example_grouped_gemm_xdl_bf16)
|
|
|
|
add_example_executable(example_grouped_gemm_xdl_int8 grouped_gemm_xdl_int8.cpp)
|
|
add_example_dependencies(example_grouped_gemm_xdl example_grouped_gemm_xdl_int8)
|
|
|
|
add_example_executable(example_grouped_gemm_xdl_fixed_nk_fp16_fp8 grouped_gemm_xdl_fixed_nk_fp16_fp8.cpp)
|
|
add_example_dependencies(example_grouped_gemm_xdl example_grouped_gemm_xdl_fixed_nk_fp16_fp8)
|
|
|
|
add_example_executable(example_grouped_gemm_multiple_d_xdl_fp16 grouped_gemm_multiple_d_xdl_fp16.cpp)
|
|
add_example_dependencies(example_grouped_gemm_xdl example_grouped_gemm_multiple_d_xdl_fp16)
|
|
|
|
if(USE_BITINT_EXTENSION_INT4)
|
|
add_example_executable(example_grouped_gemm_xdl_int4 grouped_gemm_xdl_int4.cpp)
|
|
add_example_dependencies(example_grouped_gemm_xdl example_grouped_gemm_xdl_int4)
|
|
endif()
|