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
[ONNX] Support large attribute and subgraph for large model #38793
Conversation
💊 CI failures summary and remediationsAs of commit 4b0a1a1 (more details on the Dr. CI page):
🕵️ 3 new failures recognized by patternsThe following CI failures do not appear to be due to upstream breakages: pytorch_windows_vs2019_py36_cuda10.1_build (1/3)Step: "Build" (full log | diagnosis details | 🔁 rerun)
|
0680f40
to
78c26fd
Compare
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, thanks!
About tests: since these tests won't fail even without your changes, is there a way to check external data export or files, maybe in test_utility?
@houseroad please take a look, thanks! |
@houseroad please take a look at this PR. |
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.
@houseroad has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
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.
Looks good.
@houseroad merged this pull request in eaa9107. |
Previously large tensor data in attributes and subgraphs are not stored externally. ONNX won't be able to serialize the model for cases where the total size sums up to >= 2GB. This PR enables that.