Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implementations missing for INT64 #16654

Closed
6 tasks
justinchuby opened this issue Jul 11, 2023 · 3 comments
Closed
6 tasks

Implementations missing for INT64 #16654

justinchuby opened this issue Jul 11, 2023 · 3 comments
Labels
converter:dynamo issues related supporting the PyTorch Dynamo exporter core runtime issues related to core runtime

Comments

@justinchuby
Copy link
Contributor

justinchuby commented Jul 11, 2023

  • ArgMax
  • ArgMin
  • Erf
  • Relu
  • ReduceMax
  • ReduceMin
@justinchuby justinchuby moved this to Filed Bugs in Torch Lib in onnxscript Jul 11, 2023
@justinchuby justinchuby added the core runtime issues related to core runtime label Jul 11, 2023
@skottmckay
Copy link
Contributor

We don't try and support every single type in the onnx spec for an operator as that would lead to unnecessary binary size growth for types that have no or only rare production usage.

Is there a production use case where supporting these types is required?

@justinchuby
Copy link
Contributor Author

Not that I am aware of. Just listing them as reference as we develop the conversion library for PyTorch where int64 is be supported.

@justinchuby justinchuby added the converter:dynamo issues related supporting the PyTorch Dynamo exporter label Jul 26, 2023
@thiagocrepaldi
Copy link
Contributor

closing as ORT only implement ops on demand, when needed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
converter:dynamo issues related supporting the PyTorch Dynamo exporter core runtime issues related to core runtime
Projects
Status: Filed Bugs
Development

No branches or pull requests

3 participants