You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
There really hasn't been much effort put into making it thread safe, but at the same time I'm not sure we'd get a lot of benefit from even trying. Pytorch will use up the GPU in just one thread if available, or fork a bunch on the CPU if there is no GPU
What I came to know that :
Stanza does not work with multiple async workers if they are accessing the same model.
Is there any way to handle this ?
Or Am I missing any point here ?
The text was updated successfully, but these errors were encountered: