Do you know of a way to implement something similar to this with 150 and beyond? One of the great benefits of trace flags is that we could do them per connection or per query. optimizer.step() expavg.mul(beta1).add(1 - beta1, grad) TypeError: add received an invalid combination of arguments - got (float, ), but expected one of: (float value) (torch.FloatTensor other) (torch.SparseFloatTensor other) (float value, torch. So I wrote this trigger that will work pre-150 compatibility mode. Brent like you and many others I am not a fan of turning on trace flags globally unless I’m forced to.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |