Skip to content

Fix Enzyme index manipulation spaces to match Mooncake#471

Merged
kshyatt merged 1 commit into
mainfrom
ksh/enz_im_spaces
Jul 8, 2026
Merged

Fix Enzyme index manipulation spaces to match Mooncake#471
kshyatt merged 1 commit into
mainfrom
ksh/enz_im_spaces

Conversation

@kshyatt

@kshyatt kshyatt commented Jul 1, 2026

Copy link
Copy Markdown
Member

No description provided.

@codecov

codecov Bot commented Jul 3, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.
see 53 files with indirect coverage changes

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

@kshyatt

kshyatt commented Jul 3, 2026

Copy link
Copy Markdown
Member Author

Even after a bunch of fixes for these they are still failing, and of course in a way that I cannot reproduce locally on my Ubuntu machine or on Mac M4. Maybe we should just turn these off for now, or allow-fail them, until I can figure out the cause? Sorry for messing up CI 😓

@kshyatt kshyatt force-pushed the ksh/enz_im_spaces branch 2 times, most recently from 2adb0d1 to e46cdd0 Compare July 7, 2026 04:21
@kshyatt kshyatt requested a review from lkdvos July 7, 2026 13:27
@kshyatt kshyatt force-pushed the ksh/enz_im_spaces branch from 0530e44 to 592a1d7 Compare July 7, 2026 18:16
@kshyatt

kshyatt commented Jul 7, 2026

Copy link
Copy Markdown
Member Author

After some Zulip discussion with @lkdvos , I think it makes sense to merge this with the large runner count just to unblock CI for everyone, then make another PR where we stop using test_reverse for stuff because it's extremely unstable and instead try directly using autodiff with a randomly projected gradient.

@lkdvos lkdvos left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Definitely unfortunate to have to deal with this, but in any case I do agree to just deal with the added compute cost for now, while we work on getting this sorted in the longer term.

@kshyatt kshyatt merged commit d642c40 into main Jul 8, 2026
73 checks passed
@kshyatt kshyatt deleted the ksh/enz_im_spaces branch July 8, 2026 15:06
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants