Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

[ONNX] Supporting different opset versions for torchlib registry#149901

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 ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Conversation

@shubhambhokare1
Copy link
Collaborator

  • Allows opset_version to determine which onnx decomposition to choose
  • Adds a cleanup function to modify the registry after it is built

@pytorch-bot
Copy link

pytorch-botbot commentedMar 24, 2025•
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results athud.pytorch.org/pr/149901

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit581da79 with merge base4447352 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@pytorch-botpytorch-botbot added the release notes: onnxtorch.onnx related changes that should show up in the release notes labelMar 24, 2025
@shubhambhokare1shubhambhokare1 changed the titleSupporting different opset version for torchlib registry[ONNX] Supporting different opset versions for torchlib registryMar 25, 2025
@shubhambhokare1shubhambhokare1 marked this pull request as ready for reviewMarch 25, 2025 17:09
@xadupre
Copy link
Collaborator

How do you specify opset for multiple domains?

@gramalingam
Copy link

Is there a unit test?

justinchuby reacted with thumbs up emoji

@justinchuby
Copy link
Collaborator

I recommend also implementing glu/attention. Those are the ops more frequently showing up in llms.

shubhambhokare1 reacted with heart emoji

@justinchubyjustinchuby self-assigned thisMar 25, 2025
@soulitzersoulitzer added the triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate module labelMar 26, 2025
@titaiwangmstitaiwangms added this to the2.8.0 milestoneMar 27, 2025
@shubhambhokare1
Copy link
CollaboratorAuthor

@pytorchbot rebase

pytorch-bot[bot] reacted with thumbs up emoji

@pytorchmergebot
Copy link
Collaborator

@pytorchbot started a rebase job ontorefs/remotes/origin/viable/strict. Check the current statushere

@pytorchmergebot
Copy link
Collaborator

Successfully rebasedsbhokare/vc-torchlib-pt ontorefs/remotes/origin/viable/strict, please pull locally before adding more changes (for example, viagit checkout sbhokare/vc-torchlib-pt && git pull --rebase)

@shubhambhokare1
Copy link
CollaboratorAuthor

@pytorchbot merge

pytorch-bot[bot] reacted with thumbs up emoji

@pytorchmergebot
Copy link
Collaborator

Merge started

Your change will be merged once all checks pass (ETA 0-4 Hours).

Learn more about merging in thewiki.

Questions? Feedback? Please reach out to thePyTorch DevX Team

Advanced Debugging
Check the merge workflow status
here

@pytorchmergebot
Copy link
Collaborator

The mergejob was canceled or timed out. This most often happen if two merge requests were issued for the same PR, or if merge job was waiting for more than 6 hours for tests to finish. In later case, please do not hesitate to reissue the merge command
For more information seepytorch-bot wiki.

@shubhambhokare1
Copy link
CollaboratorAuthor

@pytorchbot merge

pytorch-bot[bot] reacted with thumbs up emoji

@pytorchmergebot
Copy link
Collaborator

Merge started

Your change will be merged once all checks pass (ETA 0-4 Hours).

Learn more about merging in thewiki.

Questions? Feedback? Please reach out to thePyTorch DevX Team

Advanced Debugging
Check the merge workflow status
here

*,
trace_only:bool=False,
complex:bool=False,
opset_introduced:int=18,
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Maybe set this to _constants.TORCHLIB_OPSET too?

@justinchubyjustinchuby added the topic: new featurestopic category labelApr 9, 2025
timocafe pushed a commit to timocafe/pytorch that referenced this pull requestApr 16, 2025
…orch#149901)- Allows opset_version to determine which onnx decomposition to choose- Adds a cleanup function to modify the registry after it is builtPull Requestresolved:pytorch#149901Approved by:https://github.com/justinchuby,https://github.com/titaiwangms
amathewc pushed a commit to amathewc/pytorch that referenced this pull requestApr 17, 2025
…orch#149901)- Allows opset_version to determine which onnx decomposition to choose- Adds a cleanup function to modify the registry after it is builtPull Requestresolved:pytorch#149901Approved by:https://github.com/justinchuby,https://github.com/titaiwangms
input_names:Sequence[str]|None=None,
output_names:Sequence[str]|None=None,
opset_version:int|None=None,
opset_version:int|None=_constants.TORCHLIB_OPSET,
Copy link
Collaborator

@titaiwangmstitaiwangmsJul 25, 2025•
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Should we delete the None and line 70 and 71@justinchuby
Are there other contexts?

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

None is an allowed input in the main export api. So we accept it here

Sign up for freeto join this conversation on GitHub. Already have an account?Sign in to comment

Reviewers

@justinchubyjustinchubyjustinchuby approved these changes

@titaiwangmstitaiwangmstitaiwangms approved these changes

@wschinwschinAwaiting requested review from wschin

+2 more reviewers

@gramalingamgramalingamgramalingam left review comments

@xaduprexaduprexadupre left review comments

Reviewers whose approvals may not affect merge requirements

Labels

ciflow/trunkTrigger trunk jobs on your pull requestMergedmodule: onnxRelated to torch.onnxopen sourcerelease notes: onnxtorch.onnx related changes that should show up in the release notestopic: new featurestopic categorytriagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Projects

None yet

Milestone

2.8.0

Development

Successfully merging this pull request may close these issues.

8 participants

@shubhambhokare1@xadupre@gramalingam@justinchuby@pytorchmergebot@titaiwangms@soulitzer@pytorchbot
[8]ページ先頭
©2009-2025 Movatter.jp