leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 27 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/cute/ampere/cooperative_gemm.cu
+2 -2
View File
@@ -537,6 +537,8 @@ TEST(SM80_CuTe_Ampere, CooperativeGemmLDSMx2) {
SM75_U32x2_LDSM_N{});
}
#if (__CUDACC_VER_MAJOR__ > 12) || (__CUDACC_VER_MAJOR__ == 12 && __CUDACC_VER_MINOR__ >= 8)
TEST(SM89_CuTe_Ada, CooperativeGemm_e4m3e4m3f32_MMA) {
using TA = cutlass::float_e4m3_t;
using TB = cutlass::float_e4m3_t;
@@ -609,8 +611,6 @@ TEST(SM89_CuTe_Ada, CooperativeGemm_e5m2e5m2f32_MMA) {
test_cooperative_gemm_col_major_layout<thread_block_size, MaxVecBits, TA, TB, TC>(shape_mnk, tiled_mma);
}
#if (__CUDACC_VER_MAJOR__ > 12) || (__CUDACC_VER_MAJOR__ == 12 && __CUDACC_VER_MINOR__ >= 8)
TEST(SM89_CuTe_Ada, CooperativeGemm_e4m3e4m3f16_MMA) {
using TA = cutlass::float_e4m3_t;
using TB = cutlass::float_e4m3_t;