CUTLASS 3.8 Release (#2059)

* CUTLASS 3.8 Release

* update

* Update README.md

* Revert "Update README.md"

This reverts commit b353e36fe83e0815f99b44e46c0c95494c44726b.

* update

* update

---------

Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
This commit is contained in:
mihir-awatramani
2025-01-25 02:44:06 -05:00
committed by GitHub
co-authored by Haicheng Wu Haicheng Wu
parent 9eb01fa0b0
commit 389e493055
290 changed files with 91222 additions and 291 deletions
@@ -52,6 +52,19 @@ void initialize_gemm_reference_operations_e4m3a_e4m3out(Manifest &manifest);
void initialize_gemm_reference_operations_e5m2a_e4m3out(Manifest &manifest);
void initialize_gemm_reference_operations_e4m3a_e5m2out(Manifest &manifest);
void initialize_gemm_reference_operations_e5m2a_e5m2out(Manifest &manifest);
void initialize_gemm_reference_operations_f4_f4_f32(Manifest &manifest);
void initialize_gemm_reference_operations_f4_f6_f32(Manifest &manifest);
void initialize_gemm_reference_operations_f4_f8_f32(Manifest &manifest);
void initialize_gemm_reference_operations_f6_f4_f32(Manifest &manifest);
void initialize_gemm_reference_operations_f6_f6_f32(Manifest &manifest);
void initialize_gemm_reference_operations_f6_f8_f32(Manifest &manifest);
void initialize_gemm_reference_operations_f8_f4_f32(Manifest &manifest);
void initialize_gemm_reference_operations_f8_f6_f32(Manifest &manifest);
void initialize_block_scaled_gemm_reference_operations_fp4a_vs16(Manifest &manifest);
void initialize_block_scaled_gemm_reference_operations_fp4a_vs32(Manifest &manifest);
void initialize_block_scaled_gemm_reference_operations_mixed8bitsa(Manifest &manifest);
void initialize_gemm_reference_operations_fp8in_fp16out(Manifest &manifest);
void initialize_gemm_reference_operations_fp8in_bf16out(Manifest &manifest);
void initialize_gemm_reference_operations_fp8in_fp32out(Manifest &manifest);
@@ -89,6 +102,19 @@ void initialize_reference_operations(Manifest &manifest) {
initialize_gemm_reference_operations_fp_mixed_input(manifest);
initialize_gemm_reference_operations_int_mixed_input(manifest);
initialize_gemm_reference_operations_f4_f4_f32(manifest);
initialize_gemm_reference_operations_f4_f6_f32(manifest);
initialize_gemm_reference_operations_f4_f8_f32(manifest);
initialize_gemm_reference_operations_f6_f4_f32(manifest);
initialize_gemm_reference_operations_f6_f6_f32(manifest);
initialize_gemm_reference_operations_f6_f8_f32(manifest);
initialize_gemm_reference_operations_f8_f4_f32(manifest);
initialize_gemm_reference_operations_f8_f6_f32(manifest);
initialize_block_scaled_gemm_reference_operations_fp4a_vs16(manifest);
initialize_block_scaled_gemm_reference_operations_fp4a_vs32(manifest);
initialize_block_scaled_gemm_reference_operations_mixed8bitsa(manifest);
}
///////////////////////////////////////////////////////////////////////////////////////////////////