feat(training-utils): support device and dtype params in compute_density_for_timestep_sampling #10699
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
…ity_for_timestep_sampling
a-r-r-o-w
approved these changes
Feb 1, 2025
src/diffusers/training_utils.py
Outdated
| logit_mean: float = None, | ||
| logit_std: float = None, | ||
| mode_scale: float = None, | ||
| device: torch.device | str = "cpu", |
There was a problem hiding this comment.
Could we use Union here instead?
There was a problem hiding this comment.
sure! and i know the same change because i was trying to minimize the duplications in finetrainers 😄
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
sayakpaul
approved these changes
Feb 1, 2025
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Outdated suggestions cannot be applied.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.
What does this PR do?
the
compute_density_for_timestep_samplingfunction is defaulting to CPU-based tensor operations, which limits flexibility when working with GPUs. the function also lacks support for a generator, which made it difficult to ensure reproducibility in sampling.Additional notes
No API-breaking changes; existing calls without
deviceorgeneratorparams will default to CPU-based execution.Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@a-r-r-o-w @sayakpaul