feat: Support Qwen3.5/Qwen3.6 models convert - #118
Merged
chaokunyang merged 4 commits intoAug 20, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
This PR adds AWEX weight-update support for Qwen3.5 and Qwen3.6 Dense, MoE, and multimodal models.
It reuses the existing Qwen3/Qwen3-VL infrastructure while adding support for hybrid Gated DeltaNet attention, gated QKV layouts, vision weights, and TP/PP/EP sharding. It also filters frozen MTP weights and normalizes training/inference parameter names for SGLang compatibility.
Qwen3.6 shares the same public architecture contract as Qwen3.5, so both are supported through the same implementation.
Validation
Related issues
Does this PR introduce any user-facing change?