fix: use torch device class instead of string for compatibility with comfy memory management #200
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
…comfy memory management
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
The
comfy.model_management.free_memoryfunction expects thedeviceparam to be a<class 'torch.device'>. Currently this equality check fails because it's comparing a<class 'torch.device'>with astr.This proposed change fixes one class of OOM on my laptop's 8GB RTX 2070 GPU.
I think there is at least one other change needed to play nice with Comfy's memory management on low-VRAM GPUs. I think the main one is related to:
because the model.detach call here doesn't seem to work. If I can work that out I'll propose that change in separate pull request.