[MM]Fix bug in offload_unlocked_models() call #6450
Merged
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
lstein
requested review from
blessedcoolant,
brandonrising,
RyanJDick and
hipsterusername
as code owners
github-actions
bot
added
python
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Outdated suggestions cannot be applied.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.
Summary
When lazy offloading is false, the model locker's
unlock()method was askingoffload_unlocked_modelsto free up VRAM sufficient to load the model that is being unlocked. This was incorrect. The method should be called with a size of 0, which will have the effect of removing models until VRAM is less than or equal tomax_vram_cache.Related Issues / Discussions
Please see #6439 (review) for @RyanJDick 's discovery of this bug.
QA Instructions
Merge Plan
Merge when approved.
Checklist