Fix _init_weights to safely skip int8 quantized weights #41522
+140
−3
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
…Reddy/hf-transformers-contributions into fix-llmcompressor-error the commit.
|
[For maintainers] Suggested jobs to run (before merge) run-slow: qwen2_5_vl |
|
Can you link the issue this is fixing..? |
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Outdated suggestions cannot be applied.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.
This PR addresses a RuntimeError that occurs when loading W8A8 quantized Qwen2.5-VL models.
Changes:
_init_weightsinQwen2_5_VLPreTrainedModelto safely skip non-floating tensors (e.g., int8 quantized weights) during initialization.normal_()on integer dtypes.Note: This PR does not include the tester file
test_init_weights_safe.py; that file exists only in the fork for private testing.