Fix bug: when moving quantized model between CPU and GPU, the 4bit weights gets re-quantized #953
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Outdated suggestions cannot be applied.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.
when moving quantized model between CPU and GPU, the 4bit weights gets re-quantized, this issue is reported #937
The purposed code add a condition check and only apply the quantization if no quant_state exists.
The full test code can be found in this Colab notebook:
https://colab.research.google.com/drive/1rBWjA5VsWdTE6GiATJWHFKHbdt-HrHE4?usp=sharing