- Notifications
You must be signed in to change notification settings - Fork26.3k
[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
Uh oh!
There was an error while loading.Please reload this page.
Conversation
Signed-off-by: Justin Chu <justinchuby@users.noreply.github.com>
pytorch-botbot commentedJun 18, 2025 • edited
Loading Uh oh!
There was an error while loading.Please reload this page.
edited
Uh oh!
There was an error while loading.Please reload this page.
🔗 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 PendingAs of commitb095aea with merge basec74fd35 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
justinchuby commentedJun 18, 2025
@pytorchbot merge -i |
pytorchmergebot commentedJun 18, 2025
Merge startedYour 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 |
justinchuby commentedJun 18, 2025
@pytorchbot merge -f "all relevant tests passed" |
pytorchmergebot commentedJun 18, 2025
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 |
pytorchmergebot commentedJun 18, 2025
Merge startedYour change will be merged immediately since you used the force (-f) flag,bypassing any CI checks (ETA: 1-5 minutes). Please use Learn more about merging in thewiki. Questions? Feedback? Please reach out to thePyTorch DevX Team |
Uh oh!
There was an error while loading.Please reload this page.
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)