convert : allow vision target for DFlash/DSpark - #29339
Merged
Merged
Conversation
Resolve the target arch with get_model_architecture so vision targets (e.g. Lfm2VlForConditionalGeneration) map to their text model for the vocab. Fix double rope reorder for LFM2/LFM2.5 DSpark drafters
Contributor
Author
CISC
approved these changes
Sep 23, 2026
Member
ngxson
approved these changes
Sep 23, 2026
Collaborator
|
thanks @tdakhran for the quick response! 🚀 |
turbo-tan
pushed a commit
to turbo-tan/llama.cpp-tq3
that referenced
this pull request
Sep 24, 2026
Resolve the target arch with get_model_architecture so vision targets (e.g. Lfm2VlForConditionalGeneration) map to their text model for the vocab. Fix double rope reorder for LFM2/LFM2.5 DSpark drafters
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
PR supersedes #29332.
Resolve the target architecture with
get_model_architectureso vision targets (e.g.Lfm2VlForConditionalGeneration) map to their text model for the vocab.Additional information
Fix double rope reordering for LFM2/LFM2.5 DSpark drafters.
The first time reordering was introduced in #27383 for LFM2 text models.
Then it was implemented again in #27342, leading to double reordering.
Requirements