[Performance 1/6] use_checkpoint = False #15803
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
huchenlei
changed the title
4 tasks
wfjsw
suggested changes
May 18, 2024
| def BasicTransformerBlock_forward(self, x, context=None): | ||
| return checkpoint(self._forward, x, context) | ||
| return checkpoint(self._forward, x, context, flag=False) |
There was a problem hiding this comment.
The checkpoint here is torch.utils.checkpoint.checkpoint, and it does not have flag=False. I think you confused this with ldm.modules.diffusionmodules.util.checkpoint. The sd_hijack_checkpoint.py already removed the checkpointing in ldm, but we might need to do it on sgm as well.
There was a problem hiding this comment.
As far as I understand, what you are looking for is actually
ldm.modules.attention.BasicTransformerBlock.forward = ldm.modules.attention.BasicTransformerBlock._forward
There was a problem hiding this comment.
A closer look indicates that the checkpoint here is only called when training occurs (textual_inversion & hypernetwork) so disabling checkpoint here may be undesirable.
AUTOMATIC1111
approved these changes
Jun 8, 2024
Closed
4 tasks
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Outdated suggestions cannot be applied.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.
Description
According to lllyasviel/stable-diffusion-webui-forge#716 (comment) ,
calls to
parametersin checkpoint function is a significant overhead in A1111. However, checkpoint function is mainly used for training, disabling it does not affect inference at all.This PR disables checkpoint in A1111 in exchange for performance improvement. This reduces about 100ms/it on my local setup (4090). The duration/it before patch is ~580ms/it.
Screenshots/videos:
Checklist: