feat: support joyai-llm-flash model on npu device.#1121
Open
longhui-z wants to merge 5 commits intojd-opensource:mainfrom
Open
feat: support joyai-llm-flash model on npu device.#1121longhui-z wants to merge 5 commits intojd-opensource:mainfrom
longhui-z wants to merge 5 commits intojd-opensource:mainfrom
Conversation
longhui-z
requested review from
DongheJin,
JimHsiung,
RobbieLeung,
XuZhang99,
liutongxuan,
walsonyang and
yq33victor
as code owners
XuZhang99
changed the title
XuZhang99
reviewed
Mar 27, 2026
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces the JoyAILLMFlash model implementation for NPU, including its core logic, weight loading mechanisms, and configuration arguments. It also optimizes expert weight merging in the DeepSeek-V2 loader to support quantized formats. Feedback focuses on improving code maintainability and correctness by replacing magic numbers with named constants, using dynamic calculations for model dimensions instead of hardcoded values, and fixing signed/unsigned comparison warnings in loops.
XuZhang99
previously approved these changes
Mar 27, 2026
XuZhang99
previously approved these changes
Mar 28, 2026
liutongxuan
changed the title
XuZhang99
previously approved these changes
Mar 30, 2026
XuZhang99
approved these changes
Mar 31, 2026
RobbieLeung
reviewed
Apr 1, 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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.