Update Qwen to Flash Attn and Fix Transformers Bug #1878
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
grzegorz-roboflow
approved these changes
Jan 6, 2026
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Outdated suggestions cannot be applied.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.
Description
Qwen was slow due to not using flash attn on available hardware. Also with new transformers a new bug of loading in loras for base weights was introduced. This PR fixes both. Additionally this PR standardizes things between Qwen 2.5 and 3.
Type of change
Please delete options that are not relevant.
How has this change been tested, please provide a testcase or example of how you tested the change?
Tested Locally
Any specific deployment considerations
No
Docs