LudovicoYIN commented on PR #19632:
URL: https://github.com/apache/tvm/pull/19632#issuecomment-4570154079

   Thanks review. I updated the RNN converter to write the activated hidden 
state back to the original hidden_state tensor entry in exp_tab with 
force_override=True, so later ops observe the updated state.
   
   I also added a regression test with two consecutive RNN ops sharing the same 
hidden_state tensor to verify the second RNN consumes the updated state from 
the first one.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to