ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-19 22:39:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

test(grouped_gemm): add gtests for the example/grouped_gemm_preshuffle to ensure its integrity (#2811)

Browse Source 
* 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
This commit is contained in:
Aviral Goel
2025-09-16 18:43:30 -04:00
committed by GitHub
parent dee185d80c
commit 48e08c6429
7 changed files with 563 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
example/ck_tile/17_grouped_gemm/CMakeLists.txt
View File

@@ -1,3 +1,10 @@
add_executable(tile_example_grouped_gemm EXCLUDE_FROM_ALL grouped_gemm.cpp)
add_executable(tile_example_quant_grouped_gemm EXCLUDE_FROM_ALL quant_grouped_gemm.cpp)
add_executable(tile_example_grouped_gemm_preshuffle EXCLUDE_FROM_ALL grouped_gemm_preshuffle.cpp)
set(EXAMPLE_WEIGHT_PRESHUFFLE_COMPILE_OPTIONS)
if(CK_USE_OCP_FP8)
list(APPEND EXAMPLE_WEIGHT_PRESHUFFLE_COMPILE_OPTIONS -DCK_TILE_USE_OCP_FP8)
endif()
target_compile_options(tile_example_grouped_gemm_preshuffle PRIVATE ${EXAMPLE_WEIGHT_PRESHUFFLE_COMPILE_OPTIONS})