[Core] fix: shard loading and saving when variant is provided. #8869
Conversation
This file contains hidden or 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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
SunMarc
approved these changes
Jul 15, 2024
Member
SunMarc
left a comment
SunMarc
left a comment
There was a problem hiding this comment.
Make sense ! Thanks for fixing !
Disty0
pushed a commit
to Disty0/diffusers
that referenced
this pull request
Jul 18, 2024
…ngface#8869) fix: shard loading and saving when variant is provided.
sayakpaul
added a commit
that referenced
this pull request
Dec 23, 2024
fix: shard loading and saving when variant is provided.
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Outdated suggestions cannot be applied.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.
This is relevant for models when sharded checkpoints become an absolute necessity for loading in machines with limited RAM. With this change, we can serialize the shards in FP16 properly.
Note that this was supported before but the filename of the shard index file was incorrectly formatted. This PR fixes that and also adds a test for it.