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] Fix how shapes are computed for float4#156353

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

Closed

Conversation

@justinchuby
Copy link
Collaborator

@justinchubyjustinchuby commentedJun 18, 2025
edited
Loading

Changed the way we compute shapes for unpacked float4. Previously we always added a last dimension [2] to existing shape, but this doesn't really make sense because it prevents use from being able to represent any shape other than those with a list dim [2]. I updated the logic to be[*shape[:-1], shape[-1]*2] which doubles the last dimension. This is more in line with what we see in practice when people are using 4bit types, and it allows us to represent any shape with an even dimension at the end, which is much more reasonable in my opinion.

Also clarified in#148791 (comment)

Signed-off-by: Justin Chu <justinchuby@users.noreply.github.com>
@pytorch-bot
Copy link

pytorch-botbot commentedJun 18, 2025
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results athud.pytorch.org/pr/156353

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

❌ 1 New Failure, 13 Pending

As of commitb095aea with merge basec74fd35 (image):

NEW FAILURE - The following job has failed:

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 labelJun 18, 2025
@justinchubyjustinchuby added this to the2.8.0 milestoneJun 18, 2025
@justinchubyjustinchuby added module: onnxRelated to torch.onnx topic: improvementstopic category labelsJun 18, 2025
@justinchubyjustinchuby changed the title[ONNX] Update how shapes are computed for float4[ONNX] Fix how shapes are computed for float4Jun 18, 2025
@justinchuby
Copy link
CollaboratorAuthor

@pytorchbot merge -i

pytorch-bot[bot] reacted with thumbs up emoji

@pytorch-botpytorch-botbot added the ciflow/trunkTrigger trunk jobs on your pull request labelJun 18, 2025
@pytorchmergebot
Copy link
Collaborator

Merge started

Your change will be merged while ignoring the following 1 checks:Lint / lintrunner-clang / linux-job

Learn more about merging in thewiki.

Questions? Feedback? Please reach out to thePyTorch DevX Team

Advanced Debugging
Check the merge workflow status
here

@justinchuby
Copy link
CollaboratorAuthor

@pytorchbot merge -f "all relevant tests passed"

pytorch-bot[bot] reacted with thumbs up emoji

@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.

@pytorchmergebot
Copy link
Collaborator

Merge started

Your change will be merged immediately since you used the force (-f) flag,bypassing any CI checks (ETA: 1-5 minutes). Please use-f as last resort and instead consider-i/--ignore-current to continue the merge ignoring current failures. This will allow currently pending tests to finish and report signal before the merge.

Learn more about merging in thewiki.

Questions? Feedback? Please reach out to thePyTorch DevX Team

Advanced Debugging
Check the merge workflow status
here

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

Reviewers

@titaiwangmstitaiwangmstitaiwangms approved these changes

@shubhambhokare1shubhambhokare1Awaiting requested review from shubhambhokare1

@wschinwschinAwaiting requested review from wschin

@xaduprexadupreAwaiting requested review from xadupre

Assignees

No one assigned

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: improvementstopic category

Projects

None yet

Milestone

2.8.0

Development

Successfully merging this pull request may close these issues.

4 participants

@justinchuby@pytorchmergebot@titaiwangms@pytorchbot

[8]ページ先頭

©2009-2025 Movatter.jp