-
Notifications
You must be signed in to change notification settings - Fork 29
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
Fix linear #613
Merged
Merged
Fix linear #613
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
I went a little crazy with the fake-quant arg and the logic was ugly. Now the fake_quant arg only affects q_input. The purpose in having it at all is to allow exporting and fake eager using the same irpa file
Looks like sharktank integration test is still failing |
dan-garvey
force-pushed
the
fix_linear
branch
from
November 26, 2024 18:38
ada455c
to
e71f541
Compare
nithinsubbiah
approved these changes
Nov 26, 2024
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.
Thanks for fixing the export. I don't know if the llama data dependent test failure is expected, contingent on that good to merge.
I'm not sure this is okay to merge as is, it takes over an hour to run the punet |
ScottTodd
added a commit
that referenced
this pull request
Nov 27, 2024
Partial revert of #613. This job takes over an hour to run (specifically `test_punet_eager_fp16_validation `) and is not suitable for presubmit. This is likely also not the right file for such tests, and if it was then the specialized tests should go under the generic `test` job, not at the top of the file.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes punet regression from linear.py
I went a little crazy with the fake-quant arg and the logic was
ugly. Now the fake_quant arg only affects q_input. The purpose in having
it at all is to allow exporting and fake eager using the same irpa file