Update probe to always use cpu for loading models #6128
Merged
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Outdated suggestions cannot be applied.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.
Summary
Currently, the base model probe class doesn't identify a map device on torch loads. Due to this, if a model with gpu tensors is imported, it will attempt to use cuda whether or not it exists on the device
QA Instructions
Attempt to install this model on a device with no GPU.
Prior to this change (on MacOS):
After this change (on MacOS):
Merge Plan
Can be merged when approved