leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

v4.3 update. (#2709)

Browse Source 
* v4.3 update.

* Update the cute_dsl_api changelog's doc link

* Update version to 4.3.0

* Update the example link

* Update doc to encourage user to install DSL from requirements.txt

---------

Co-authored-by: Larry Wu <larwu@nvidia.com>
This commit is contained in:
Junkai-Wu
2025-10-21 14:26:30 -04:00
committed by GitHub
co-authored by Larry Wu
parent e6e2cc29f5
commit b1d6e2c9b3
244 changed files with 59272 additions and 10455 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/70_blackwell_gemm/CMakeLists.txt
+1 -1
View File
@@ -33,7 +33,7 @@ set(TEST_SWIZZLE_2 --swizzle=2)
set(TEST_SWIZZLE_5 --swizzle=5)
set(TEST_SWIZZLE_5_UNEVEN --swizzle=5 --m=4096 --n=16384)
if(CUTLASS_NVCC_ARCHS STREQUAL "100a" OR CUTLASS_NVCC_ARCHS STREQUAL "100f" OR CUTLASS_NVCC_ARCHS STREQUAL "101a" OR CUTLASS_NVCC_ARCHS STREQUAL "101f" OR CUTLASS_NVCC_ARCHS STREQUAL "103a" OR CUTLASS_NVCC_ARCHS STREQUAL "103f")
if(CUTLASS_NVCC_ARCHS MATCHES "100a|100f|101a|101f|103a|103f")
cutlass_example_add_executable(
70_blackwell_fp16_gemm
70_blackwell_fp16_gemm.cu