Allow searching for .pt2 archives #6689
Merged
Conversation
This file contains 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
ltdrdata
added
the
Good PR
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Outdated suggestions cannot be applied.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.
Pytorch 2.6 introduces a new format for AOTInductor modules, which uses the extension
.pt2.I've had good results compiling comfyui models to AOTInductor modules and then loading them back in ComfyUI: you get the same performance improvements as
torch.compile, but without the overhead of compiling at runtime. At the moment there's no standardization for the metadata contained in an AOTInductor archive, and all the config/tensor name information is stripped, so to actually detect what kind of model is being loaded is a question for the future. For now, we can make it easier to load AOTI archives in custom nodes by adding the format as a known pytorch extension.