[Flux] Optimize guidance creation in flux pipeline by moving it outside the loop #9153
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
chengzeyi
changed the title
sayakpaul
reviewed
Aug 13, 2024
Comment on lines
+680
to
+685
| # handle guidance | ||
| if self.transformer.config.guidance_embeds: | ||
| guidance = torch.full([1], guidance_scale, device=device, dtype=torch.float32) | ||
| guidance = guidance.expand(latents.shape[0]) | ||
| else: | ||
| guidance = None |
|
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. |
5 tasks
sayakpaul
added a commit
that referenced
this pull request
Dec 23, 2024
…de the loop (#9153) * optimize guidance creation in flux pipeline by moving it outside the loop * use torch.full instead of torch.tensor to create a tensor with a single value --------- Co-authored-by: Sayak Paul <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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Outdated suggestions cannot be applied.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?
Optimize guidance creation in flux pipeline by moving it outside the loop and using
torch.full()instead oftorch.tensor.By doing so, we reduce number of the unnecessary implict CUDA synchronizations caused by creating a device tensor from a list.
I observe a little performance gain (1%-2%) by applying this fix.
Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.