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
[DCP][state_dict] DCP state_dict cannot correctly find FQN when the leaf module is wrapped by FSDP #115592
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/115592
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (2 Unrelated Failures)As of commit db2d941 with merge base c70f995 (): FLAKY - The following job failed but was likely due to flakiness present on trunk:
UNSTABLE - The following job failed but was likely due to flakiness present on trunk and has been marked as unstable:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This pull request was exported from Phabricator. Differential Revision: D52049293 |
@@ -181,7 +191,7 @@ def test_fsdp(self) -> None: | |||
{ | |||
"use_orig_params": [True, False], | |||
"use_composable": [True, False], | |||
"use_dtensor": [True, False], | |||
"use_dtensor": [True,False], |
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.
This seems unintentional?
5ebd7b8
to
ee40a3b
Compare
…eaf module is wrapped by FSDP (pytorch#115592) Summary: The original logic has an incorrect assumption that there is at one object name left when traversing the module tree. This is not correct when the leaf module is wrapped by FSDP. Test Plan: CI Differential Revision: D52049293
This pull request was exported from Phabricator. Differential Revision: D52049293 |
ee40a3b
to
4b3ee0c
Compare
…eaf module is wrapped by FSDP (pytorch#115592) Summary: The original logic has an incorrect assumption that there is at one object name left when traversing the module tree. This is not correct when the leaf module is wrapped by FSDP. Test Plan: CI Differential Revision: D52049293
This pull request was exported from Phabricator. Differential Revision: D52049293 |
4b3ee0c
to
72e3d30
Compare
…eaf module is wrapped by FSDP (pytorch#115592) Summary: The original logic has an incorrect assumption that there is at one object name left when traversing the module tree. This is not correct when the leaf module is wrapped by FSDP. Test Plan: CI Differential Revision: D52049293
This pull request was exported from Phabricator. Differential Revision: D52049293 |
This pull request was exported from Phabricator. Differential Revision: D52049293 |
72e3d30
to
4187e7b
Compare
…eaf module is wrapped by FSDP (pytorch#115592) Summary: The original logic has an incorrect assumption that there is at one object name left when traversing the module tree. This is not correct when the leaf module is wrapped by FSDP. Test Plan: CI Differential Revision: D52049293
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.
LGTM!
4187e7b
to
53c4d33
Compare
…eaf module is wrapped by FSDP (pytorch#115592) Summary: The original logic has an incorrect assumption that there is at one object name left when traversing the module tree. This is not correct when the leaf module is wrapped by FSDP. Test Plan: CI Reviewed By: wz337 Differential Revision: D52049293
This pull request was exported from Phabricator. Differential Revision: D52049293 |
…eaf module is wrapped by FSDP (pytorch#115592) Summary: The original logic has an incorrect assumption that there is at one object name left when traversing the module tree. This is not correct when the leaf module is wrapped by FSDP. Test Plan: CI Reviewed By: wz337 Differential Revision: D52049293
53c4d33
to
db2d941
Compare
This pull request was exported from Phabricator. Differential Revision: D52049293 |
@pytorchbot merge (Initiating merge automatically since Phabricator Diff has merged) |
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 |
…eaf module is wrapped by FSDP (pytorch#115592) Summary: The original logic has an incorrect assumption that there is at one object name left when traversing the module tree. This is not correct when the leaf module is wrapped by FSDP. Test Plan: CI Differential Revision: D52049293 Pull Request resolved: pytorch#115592 Approved by: https://github.com/wz337
…eaf module is wrapped by FSDP (pytorch#115592) Summary: The original logic has an incorrect assumption that there is at one object name left when traversing the module tree. This is not correct when the leaf module is wrapped by FSDP. Test Plan: CI Differential Revision: D52049293 Pull Request resolved: pytorch#115592 Approved by: https://github.com/wz337
…eaf module is wrapped by FSDP (pytorch#115592) Summary: The original logic has an incorrect assumption that there is at one object name left when traversing the module tree. This is not correct when the leaf module is wrapped by FSDP. Test Plan: CI Differential Revision: D52049293 Pull Request resolved: pytorch#115592 Approved by: https://github.com/wz337
…eaf module is wrapped by FSDP (pytorch#115592) Summary: The original logic has an incorrect assumption that there is at one object name left when traversing the module tree. This is not correct when the leaf module is wrapped by FSDP. Test Plan: CI Differential Revision: D52049293 Pull Request resolved: pytorch#115592 Approved by: https://github.com/wz337
…eaf module is wrapped by FSDP (pytorch#115592) Summary: The original logic has an incorrect assumption that there is at one object name left when traversing the module tree. This is not correct when the leaf module is wrapped by FSDP. Test Plan: CI Differential Revision: D52049293 Pull Request resolved: pytorch#115592 Approved by: https://github.com/wz337
Summary: The original logic has an incorrect assumption that there is at one object name left when traversing the module tree. This is not correct when the leaf module is wrapped by FSDP.
Test Plan: CI
Differential Revision: D52049293
cc @mrshenli @pritamdamania87 @zhaojuanmao @satgera @rohan-varma @gqchen @aazzolini @osalpekar @jiayisuse @H-Huang @kwen2501 @awgu @penguinwu @XilunWu @wanchaol @fduwjj @wz337 @tianyu-l @wconstab @yf225