chore: rm extra norm in py model #362
Closed
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
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR attempts to remove the final normalization layer from Python model implementations, but this change introduces a critical bug that will break model inference.
Key Issue
The PR removes self.norm(hidden_states) from the forward methods of both Qwen3Model and GenericMoeModel. However, the C++ wrapper (PyWrappedModel::forward) passes skip_final_layernorm=true to the post-processing layer, which means it expects the Python model to apply the final normalization. Without this normalization:
- Hidden states will not be properly normalized before computing logits
- Model outputs will be incorrect
- Inference results will be degraded or broken
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| rtp_llm/models_py/model_desc/qwen3.py | Bug: Removes required final normalization from Qwen3Model.forward() |
| rtp_llm/models_py/model_desc/generic_moe.py | Bug: Removes required final normalization from GenericMoeModel.forward() |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.