leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 24 Packages Projects Releases Wiki Activity

update 3.8 v2 (#2112)

Browse Source 
* update 3.8 v2

* update 3.8

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
This commit is contained in:
Yujia Zhai
2025-02-19 22:03:14 -05:00
committed by GitHub
co-authored by yuzhai
parent e9627ce55b
commit b84e9802d8
166 changed files with 3986 additions and 4037 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/unit/gemm/device/CMakeLists.txt
+1 -5
View File
@@ -51,12 +51,8 @@ endfunction()
################################################################################
add_subdirectory(sm100_blockscaled_tensorop_gemm)
add_subdirectory(sm100_tensorop_gemm)
cutlass_test_unit_gemm_device_add_executable(
cutlass_test_unit_gemm_device_simt
@@ -833,7 +829,7 @@ endif()
if(NOT CUTLASS_NVCC_ARCHS STREQUAL "100")
if (CUTLASS_NVCC_ARCHS MATCHES 100a)
cutlass_test_unit_gemm_device_add_executable(
cutlass_test_unit_gemm_device_16b_tensorop_sm100_ptr_array