Fix: Skip weight initialization for quantized int8 models#39491
Open
imjbassi wants to merge 1 commit intohuggingface:mainfrom
Open
Fix: Skip weight initialization for quantized int8 models#39491imjbassi wants to merge 1 commit intohuggingface:mainfrom
imjbassi wants to merge 1 commit intohuggingface:mainfrom
Conversation
Member
evalstate
added a commit
to evalstate/transformers
that referenced
this pull request
Apr 29, 2026
This was referenced Apr 29, 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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #39366 by skipping weight initialization when all model parameters are non-floating-point types (e.g., int8 from W8A8 quantized models). This avoids a RuntimeError from PyTorch's
normal_()function, which cannot handle integer dtypes.Adds a conditional check inside
_load_pretrained_modelto skipself.initialize_weights()when appropriate.Tested to ensure model loads without crashing for quantized cases.