Conversation
DN6
reviewed
Mar 25, 2026
| model_quantized.to(torch_device) | ||
|
|
||
| inputs = self.get_dummy_inputs() | ||
| model_dtype = next(model_quantized.parameters()).dtype |
Collaborator
There was a problem hiding this comment.
This would affect all quantization backends? e.g. With a GGUF backend the dtype could end up as int8 and potentially cast inputs into int8?
Also prefer to avoid casting inputs post fetching from self.get_dummy_inputs() within a test if we can avoid it.
Member
Author
There was a problem hiding this comment.
Where should it go then? Should we implement a custom get_dummy_inputs() for torchao tests? I think it's reasonably safe to keep the dtypes of the inputs to bfloat16 there because that will replicate what we do in actual pipelines. LMK.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Surfaced in #13291 (comment). Cc: @howardzhang-cv