bugfix: update Glm5-W8A8 & Draft Model on npu device.#1193
Merged
liutongxuan merged 2 commits intojd-opensource:mainfrom Apr 27, 2026
Merged
bugfix: update Glm5-W8A8 & Draft Model on npu device.#1193liutongxuan merged 2 commits intojd-opensource:mainfrom
liutongxuan merged 2 commits intojd-opensource:mainfrom
Conversation
Contributor
There was a problem hiding this comment.
Code Review
This pull request adds support for the glm_moe_dsa model type to the MTP export utility and introduces an optional rot linear layer to the MTP model base. It also updates the DeepSeek V3.2 decoder loader to handle additional quantization parameters for the indexer. Feedback highlights a logic error in the Python export script regarding the detection and mapping of rot.weight and identifies several instances where constant arguments in C++ were not annotated according to the style guide.
RobbieLeung
approved these changes
Apr 10, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.