It might cause TupleTypeNode to be printed incorrectly. it doesnt show in http://ci.tvm.ai:8080/blue/organizations/jenkins/tvm/detail/PR-1989/1/pipeline/141, but if you run it on local machine you will see what get compared being NodeBase and TupleType. Also as a side thought can we write a giant macro that make sure everything get did right (all field get visited, typekey match, declare_node_type_info match, etc?) I can do some macro metaprogramming, so I can take up the work.
Name |
Last commit
|
Last update |
---|---|---|
.. | ||
attrs | Loading commit data... | |
base.h | Loading commit data... | |
environment.h | Loading commit data... | |
error.h | Loading commit data... | |
expr.h | Loading commit data... | |
expr_functor.h | Loading commit data... | |
logging.h | Loading commit data... | |
op.h | Loading commit data... | |
pass.h | Loading commit data... | |
type.h | Loading commit data... |