mtmd-helper : bug fix to token batching in mtmd #13650
Merged
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
ngxson
approved these changes
May 20, 2025
Collaborator
ngxson
left a comment
ngxson
left a comment
There was a problem hiding this comment.
Hmm yeah thanks for noticing, I think I mistakenly left the i variable there from the non-batching code
ngxson
changed the title
Co-authored-by: Xuan-Son Nguyen <[email protected]>
infil00p
pushed a commit
to baseweight/llama.cpp
that referenced
this pull request
May 22, 2025
* Update mtmd-helper.cpp * Update tools/mtmd/mtmd-helper.cpp Co-authored-by: Xuan-Son Nguyen <[email protected]> --------- Co-authored-by: Xuan-Son Nguyen <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
From my understanding, we should be setting each field in the tokens batch using the current
text_batch.n_tokenscounter, instead of the outericounter.If the outer
n_tokens>n_batch, the original code gives a segmentation fault because each batch is only initialised withn_batchnumber of spaces, butiwill increase to the number of overalln_tokens.