| 228 | } |
| 229 | |
| 230 | int igemmlt_8( |
| 231 | cublasLtHandle_t ltHandle, int m, int n, int k, const int8_t* A, const int8_t* B, void* C, float* row_scale, |
| 232 | int lda, int ldb, int ldc, cudaStream_t stream |
| 233 | ) { |
| 234 | return igemmlt<8, 0>(ltHandle, m, n, k, A, B, C, row_scale, lda, ldb, ldc, stream); |
| 235 | } |
| 236 | |
| 237 | int igemmlt_8_rowscale( |
| 238 | cublasLtHandle_t ltHandle, int m, int n, int k, const int8_t* A, const int8_t* B, void* C, float* row_scale, |