Function cigemmlt_8_rowscale

csrc/pythonInterface.cpp:538–543

}

int cigemmlt_8_rowscale(
    Context* context, int m, int n, int k, const int8_t* A, const int8_t* B, void* C, float* row_scale, int lda,
    int ldb, int ldc, cudaStream_t stream
) {
    return igemmlt_8_rowscale((cublasLtHandle_t)context->m_handle, m, n, k, A, B, C, row_scale, lda, ldb, ldc, stream);
}

void cdequant_mm_int32_fp16(
    int* A, float* rowStats, float* colStats, half* out, half* bias, int numRows, int numCols, cudaStream_t stream