leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 28 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
test/unit/gemm/device/CMakeLists.txt
+3 -1
View File
@@ -645,6 +645,7 @@ endif()
if (CUTLASS_NVCC_DEVICE_COMPILE)
if (NOT CUTLASS_NVCC_ARCHS MATCHES 101|101a|101f|110|110a|110f)
cutlass_test_unit_gemm_device_add_executable(
cutlass_test_unit_gemm_device_blas3
@@ -808,7 +809,7 @@ cutlass_test_unit_gemm_device_add_executable(
hemm_cf64_cf64_cf64_tensor_op_f64_sm90.cu
)
if (NOT CUTLASS_NVCC_ARCHS MATCHES 100f|101|101a|101f|103|103a|103f)
if (NOT CUTLASS_NVCC_ARCHS MATCHES 100f|101|101a|101f|110|110a|110f|103|103a|103f)
cutlass_test_unit_gemm_device_add_executable(
cutlass_test_unit_gemm_device_blas3_gaussian
@@ -844,6 +845,7 @@ cutlass_test_unit_gemm_device_add_executable(
her2k_cf64n_cf64n_tensor_op_f64_grouped_sm80.cu
her2k_cf64h_cf64n_tensor_op_f64_grouped_sm80.cu
)
endif()
endif()