Add TorchAO disk group offload support#13875
Draft
hlky wants to merge 1 commit into
Draft
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Split out from #13719 after review feedback to keep the TorchAO safetensors PR focused on save/load.
This follow-up contains only the TorchAO disk group-offload work:
Validation so far:
python -m ruff check src/diffusers/hooks/group_offloading.py tests/quantization/torchao/test_torchao.pypython -m compileall -q src/diffusers/hooks/group_offloading.py tests/quantization/torchao/test_torchao.pyOpening as draft because the parent save/load PR should land first, and this PR may need review after that scope settles.