Remove blocking call from timestep embedding of Chroma#8255
Merged
comfyanonymous merged 1 commit intoComfy-Org:masterfrom May 23, 2025
Merged
Remove blocking call from timestep embedding of Chroma#8255comfyanonymous merged 1 commit intoComfy-Org:masterfrom
comfyanonymous merged 1 commit intoComfy-Org:masterfrom
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This creates a tensor on device to avoid an unnecessary sync in the Chroma model forward pass. Part of a series of PRs I'm creating. Combined with #7152, another PR to make a CPU copy of sampler sigmas for use in control flow (since control flow needs these as python scalars to work), and optionally code to support computing latent previews/transferring them to CPU on a separate CUDA stream as I did here for webui forge (may be more complicated since comfyui doesn't seem to process previews in a separate thread from the main one), I am seeing a roughly 7% overall speed boost.