mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-11-10 09:34:01 +08:00
realAsma
9409412051
## What does this PR do? **Type of change:** Bug fix [aq_Qwen3-235B-A22B-Thinking-2507_scores.html](https://github.com/user-attachments/files/23915284/aq_Qwen3-235B-A22B-Thinking-2507_scores.html) **Overview:** For Qwen3 MoE, sensitivity should be measured at `layer.x.mlp` not `layer.x.mlp.experts` (`layer.x.mlp.experts` module forward is never called. Hence sensitivity was not correctly estimated previously). After this PR, Qwen3 MoE sensitivity is correctly estimated. (See attached file) ## Usage <!-- You can potentially add a usage example below. --> ```python # Add a code snippet demonstrating how to use this ``` ## Testing <!-- Mention how have you tested your change if applicable. --> ## Before your PR is "*Ready for review*" <!-- If you haven't finished some of the above items you can still open `Draft` PR. --> - **Make sure you read and follow [Contributor guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)** and your commits are signed. - **Is this change backward compatible?**: Yes/No <!--- If No, explain why. --> - **Did you write any new necessary tests?**: Yes/No - **Did you add or update any necessary documentation?**: Yes/No - **Did you update [Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**: Yes/No <!--- Only for new features, API changes, critical bug fixes or bw breaking changes. --> ## Additional Information <!-- E.g. related issue. --> --------- Signed-off-by: realAsma <akuriparambi@nvidia.com>