Save partial imatrix data #7910
Open
+18
−11
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
mofosyne
added
the
Review Complexity : Medium
|
Not sure about this change - it's better to just have proper imatrix data instead of adding extra logic. If you have imatrices with |
Being able to load a partial imatrix is essential for the already existing resume-functionality, adding the recovery of corrupted data was just an afterthought since I can't see any downside to it, it will effectively erase the bad data. |
vignesh1507
reviewed
Oct 7, 2024
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Outdated suggestions cannot be applied.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.
Allow saving partial imatrix data again to be able to load it later with
--in-file.If an imatrix with partial or otherwise non-normal data is attempted used for quantization, remove the affected entries with a warning, non-imatrix quantization will then be performed on these tensors (if allowed).
Also allow resuming with a previously generated imatrix with non-normal data by clearing the affected data.