update 3.8 v2 (#2112)

* 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
+1 -1
View File
@@ -49,7 +49,7 @@ set(TEST_GEN_REMAP --b=2 --h=4 --h_k=2 --k=512 --d=128 --verify --remap)
set(TEST_GEN_CACHEONLY --b=2 --h=4 --h_k=2 --k=512 --d=128 --verify --cache-only)
if(NOT WIN32 AND (NOT (CMAKE_CXX_COMPILER_ID MATCHES "Clang")))
if(NOT CUTLASS_NVCC_ARCHS STREQUAL "100")
if (CUTLASS_NVCC_ARCHS MATCHES 100a)
cutlass_example_add_executable(
77_blackwell_fmha_fp8
77_blackwell_fmha.cu