Toby Roseman
Toby Roseman
> There is also a big difference in execution time between PyTorch and CoreML text models. > > PyTorch: 0.27843 seconds CoreML: 7.80541 seconds Are you measuring performance on the...
We did not remove support for `torch.baddbmm`. We never supported it. We're already tracking that issue in #1555. It seems the new version of PyTorch uses this op more often...
@AustinStarnes - can you give us a minimal self-containded example, something which uses a much simpler model?
Can you give us a minimal example to reproduce this problem (i.e. something which doesn't use an external model)?
I'm not able to execute your code. This line: `model_unbind.qkv.weight[:] = model.qkv.weight` produces the following error: `RuntimeError: a view of a leaf Variable that requires grad is being used in...
@dncnbuck - could you please add a unit test which fails without your fix but passes with the fix?
Can you give us a minimal example to reproduce this problem (i.e. something which doesn't use an external model)?
@GaganNarula - please open a pull request with this fix.
Fixed via #1609
I am not able to run the referenced code since we don't have the data. Here is a much more direct way to trigger the issue: ```python import torch import...