-
Notifications
You must be signed in to change notification settings - Fork 25.7k
Inductor cpp wrapper: fix buffer free in non-AOT mode #114741
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
Conversation
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/114741
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 22c23ab with merge base 0ced55e ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
@pytorchbot rebase |
|
@pytorchbot started a rebase job onto refs/remotes/origin/viable/strict. Check the current status here |
We found performance regression when using cpp wrapper in non-AOT mode due to the change in #110892. #110892 only handles the buffer cache in AOT mode but removes the `reset` call without checking whether AOT mode is on or off. This PR updates the buffer free change to only happen when `V.graph.aot_mode is True`. cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
|
Successfully rebased |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Better to add a test that counts the reset() statements.
We found performance regression when using cpp wrapper in non-AOT mode due to the change in #110892. #110892 only handles the buffer cache in AOT mode but removes the `reset` call without checking whether AOT mode is on or off. This PR updates the buffer free change to only happen when `V.graph.aot_mode is True`. cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
We found performance regression when using cpp wrapper in non-AOT mode due to the change in #110892. #110892 only handles the buffer cache in AOT mode but removes the `reset` call without checking whether AOT mode is on or off. This PR updates the buffer free change to only happen when `V.graph.aot_mode is True`. cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
Test has been added. |
|
@pytorchbot merge |
Merge failedReason: This PR needs a If not, please add the To add a label, you can comment to pytorchbot, for example For more information, see Details for Dev Infra teamRaised by workflow job |
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
We found performance regression when using cpp wrapper in non-AOT mode due to the change in pytorch#110892. pytorch#110892 only handles the buffer cache in AOT mode but removes the `reset` call without checking whether AOT mode is on or off. This PR updates the buffer free change to only happen when `V.graph.aot_mode is True`. Pull Request resolved: pytorch#114741 Approved by: https://github.com/jgong5, https://github.com/desertfire
Stack from ghstack (oldest at bottom):
We found performance regression when using cpp wrapper in non-AOT mode due to the change in #110892.
#110892 only handles the buffer cache in AOT mode but removes the
resetcall without checking whether AOT mode is on or off. This PR updates the buffer free change to only happen whenV.graph.aot_mode is True.cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @peterbell10 @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @aakhundov @ColinPeppler