fix(gguf_inference): resolve mmproj filename collision#9
Open
avan06 wants to merge 1 commit intodseditor:mainfrom
Open
fix(gguf_inference): resolve mmproj filename collision#9avan06 wants to merge 1 commit intodseditor:mainfrom
avan06 wants to merge 1 commit intodseditor:mainfrom
Conversation
Refactored SUGGESTED_MMPROJ in gguf_inference.py to use a dictionary structure, allowing unique local filenames for different model versions. Fixed an issue where Qwen2.5-VL and Qwen3-VL mmproj files would overwrite each other due to identical remote filenames. Updated the download and pathing logic to ensure the correct version-specific mmproj is loaded during inference.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Refactored SUGGESTED_MMPROJ in gguf_inference.py to use a dictionary structure, allowing unique local filenames for different model versions.
Fixed an issue where Qwen2.5-VL and Qwen3-VL mmproj files would overwrite each other due to identical remote filenames.
Updated the download and pathing logic to ensure the correct version-specific mmproj is loaded during inference.
While using the GGUFInference node in ListHelper with QwenVL models, I encountered a filename conflict issue with the mmproj files. Since Qwen2.5-VL and Qwen3-VL utilize different mmproj structures, but the current script downloads both under the same name (mmproj-F16.gguf), it causes a conflict. Once one version is downloaded, the other model is forced to use the same file, leading to loading failures when switching versions. I have updated the logic to rename these files based on their specific versions during the download phase, which effectively resolves the conflict. Thank you.