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

Add support for mixed 4-bit/8-bit data types GEMM (#1413)

Browse Source 
* Add support for mixed 4-bit/8-bit data types GEMM

* fix ( and )

---------

Co-authored-by: Aleksandar Samardžić <asamardzic@matf.bg.ac.rs>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
This commit is contained in:
Aleksandar Samardžić
2024-08-29 23:11:06 -04:00
committed by GitHub
co-authored by Aleksandar Samardžić Haicheng Wu
parent f7b19de32c
commit e1976daacc
15 changed files with 960 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/unit/gemm/device/CMakeLists.txt
+6
View File
@@ -264,6 +264,9 @@ cutlass_test_unit_add_executable(
gemm_universal_s8t_f16n_f16t_mixed_input_tensor_op_f16_sm80.cu
gemm_universal_u8t_f16n_f16t_mixed_input_tensor_op_f16_sm80.cu
gemm_universal_s4t_s8n_s32t_mixed_input_tensor_op_s32_sm80.cu
gemm_universal_s4t_s8n_s8t_mixed_input_tensor_op_s32_sm80.cu
# Upcast on Operand B
gemm_universal_f16t_s8n_f32t_mixed_input_tensor_op_f32_sm80.cu
gemm_universal_f16t_u8n_f32t_mixed_input_tensor_op_f32_sm80.cu
@@ -277,6 +280,9 @@ cutlass_test_unit_add_executable(
gemm_universal_f16t_s8n_f16t_mixed_input_tensor_op_f16_sm80.cu
gemm_universal_f16t_u8n_f16t_mixed_input_tensor_op_f16_sm80.cu
gemm_universal_s8t_s4n_s32t_mixed_input_tensor_op_s32_sm80.cu
gemm_universal_s8t_s4n_s8t_mixed_input_tensor_op_s32_sm80.cu
)
cutlass_test_unit_add_executable(