improve the code of _CudaBLASMatrixMULList

source/tensor/core/arithmetic/XTensorBLAS.cu

@@ -253,7 +253,7 @@ void _CudaBLASMatrixMULList(cublasHandle_t * handle,
 
     if (isUniform) {
         XMem * mem = a0->mem;
-        if (isStrided && a->count > 1) {
+        if (isStrided) {
             _CudaBLASMatrixMULBatchedStrided(handle,
                                              a0->data, transposedA, a0->dataType, strideA / a0->unitSize,
                                              b0->data, transposedB, b0->dataType, strideB / b0->unitSize,