Is there any room for gpu memory improvements?

[realiti4]

Hi, it looks like the loop inside the decoder consumes too much gpu memory very quickly if you try to increase history size because we keep tracking hidden and cell units. I wonder if there is room for any improvements. Would it kill the purpose of the model if we detach some things somehow?

[Seanny123]

I have no idea. I have no experience optimizing GPU execution. Are you using the `jit` branch?

…

On Sat, 15 Feb 2020 at 06:02, Onur ***@***.***> wrote: Hi, it looks like the loop inside the decoder consumes too much gpu memory very quickly if you try to increase history size because we keep tracking hidden and cell units. I wonder if there is room for any improvements. Would it kill the purpose of the model if we detach some things somehow? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#17?email_source=notifications&email_token=AAOUO2N7TYNQLXRFOLUSDXLRC7DUJA5CNFSM4KVXTJM2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4INYMT3A>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAOUO2N34DKS7JAAYH6CKGTRC7DUJANCNFSM4KVXTJMQ> .

[realiti4]

Hi, I was using master.