It is determined GraphFuse.
fe.flatten_data = (pattern_vec[root_id] == kElemWise ||
inode.source->op() == assign_op);
If a buffer gets stride configured, flatten data causes problem.
For example, for a input tensor [2, 3] , As long as shape is flattened, generated host side code will check whether the stride[0] of input is 1, but graph runtime uses real shape and real stride in which stride[0] is 3
I am wondering whether it is safe to disable this?