leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 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
2025-10-22 02:26:30 +08:00
committed by GitHub
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

40
tools/library/src/reference/gemm_f4_f8_f32.cu
View File

@@ -99,6 +99,46 @@ void initialize_gemm_reference_operations_f4_f8_f32(Manifest &manifest) {
float // ElementD
>(manifest);
// 1.
make_gemm_real_canonical_layouts<
float_e2m1_t, // ElementA
float_e5m2_t, // ElementB
half_t, // ElementC
float, // ElementScalar
float, // ElementAccumulator
float_e4m3_t // ElementD
>(manifest);
// 2.
make_gemm_real_canonical_layouts<
float_e2m1_t, // ElementA
float_e5m2_t, // ElementB
half_t, // ElementC
float, // ElementScalar
float, // ElementAccumulator
float_e5m2_t // ElementD
>(manifest);
// 3.
make_gemm_real_canonical_layouts<
float_e2m1_t, // ElementA
float_e5m2_t, // ElementB
half_t, // ElementC
float, // ElementScalar
float, // ElementAccumulator
half_t // ElementD
>(manifest);
// 4.
make_gemm_real_canonical_layouts<
float_e2m1_t, // ElementA
float_e5m2_t, // ElementB
float, // ElementC
float, // ElementScalar
float, // ElementAccumulator
float // ElementD
>(manifest);
}
///////////////////////////////////////////////////////////////////////////////////////////////////