Fix quantized model dispatch with device_map='auto'#39468
Open
Krish0909 wants to merge 2 commits intohuggingface:mainfrom
Open
Fix quantized model dispatch with device_map='auto'#39468Krish0909 wants to merge 2 commits intohuggingface:mainfrom
Krish0909 wants to merge 2 commits intohuggingface:mainfrom
Conversation
- Skip dispatch_model for bitsandbytes quantized models - Quantized models are already placed on correct devices - Fixes ValueError: .to is not supported for 4-bit/8-bit models
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Fixes issue #39461 where quantized models fail to load with
device_map="auto"on Linux but work on Windows.Root cause:
dispatch_modelcallsmodel.to(device)on bitsandbytes quantized models, which isn't supported. Platform differences in device detection/handling cause this code path to be hit on Linux but not Windows.Fix: Skip
dispatch_modelfor bitsandbytes quantized models since they're already correctly placed during quantization.Fixes #39461
please verify quantization experts (bitsandbytes, autogpt): @SunMarc @MekkCyber