Add final norm for LoRA models - #1446
Merged
Merged
Conversation
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR fixes issues related to the handling of LoRA models by adding support for identifying the final normalization layer and cleaning up model builder class methods. Key changes include renaming function parameters in packed MatMul calls to ensure consistency and updating the final norm detection logic (via has_final_norm) to handle PEFT models correctly.
Comments suppressed due to low confidence (1)
src/python/py/models/builder.py:920
- The parameter 'basename' replaces the previous 'name' in this function; please ensure that all call sites are updated consistently to prevent mismatches between the naming of the MatMul nodes.
def make_packed_matmul_fp16_or_fp32(self, q_matmul, k_matmul, v_matmul, basename, root_input, **kwargs):
Ryan Hill (RyanUnderhill)
approved these changes
May 7, 2025
Ryan Hill (RyanUnderhill)
pushed a commit
that referenced
this pull request
May 12, 2025
### Description This PR adds the missing pattern to identify the final norm layer in LoRA models. It also cleans up some of the classes in the model builder. ### Motivation and Context The missing final norm layer in LoRA models caused the generated LoRA models to be incorrect.
Merged
Baiju Meswani (baijumeswani)
added a commit
that referenced
this pull request
May 14, 2025
Address previous PR review comments from #1470 (#1473) Address QNN specific regressions (#1470) Fix array eos_token_id handling (#1463) Constrained decoding integration (#1381) Remove BF16 CPU from valid GQA configuration (#1469) Avoid adding providers if not requested (#1464) Persist provider options across ClearProviders, AppendProvider where possible (#1454) Fix accuracy issues with Gemma models (#1448) Add bfloat16 support in model builder (#1447) Add final norm for LoRA models (#1446) Update version to 0.8.0-rc3 --------- Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com> Co-authored-by: Nenad Banfic <46795300+nenad1002@users.noreply.github.com> Co-authored-by: Nenad Banfic <nebanfic@microsoft.com> Co-authored-by: Baiju Meswani <bmeswani@microsoft.com> Co-authored-by: Abhishek Jindal <abjindal@microsoft.com> Co-authored-by: Ying Xiong <yingxiong@microsoft.com> Co-authored-by: Michał Moskal <michal@moskal.me> Co-authored-by: Kunal Vaishnavi <kvaishnavi@microsoft.com>
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.
Description
This PR adds the missing pattern to identify the final norm layer in LoRA models. It also cleans up some of the classes in the model builder.
Motivation and Context
The missing final norm layer in LoRA models caused the generated LoRA models to be incorrect.