fix(qwen3.5): read layer types from model config - #612
Merged
pan-x-c merged 1 commit intoJul 31, 2026
Conversation
Contributor
|
Caution The consumer version of Gemini Code Assist on GitHub has been sunset. All code review activity has officially ceased. |
Collaborator
|
/unittest-module-trainer |
unittest: Run #1847
🎉 All tests passed!Github Test Reporter by CTRF 💚 |
pan-x-c
approved these changes
Jul 31, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
With Ulysses sequence parallelism enabled, newer Qwen3.5 model implementations may not expose
layer_typeon each decoder layer. The monkey patch then fails before patching linear-attention layers with:Fix
Read each layer type from the model configuration's
layer_typeslist instead of relying on a per-layer attribute. This keeps linear-attention layer detection aligned with the model config.