Open
Conversation
Author
class TracedPosArgOnlyModuleWrapper(torch.nn.Module):
def __init__(self, module, *, training=None):
super().__init__()
self.module = module
if training is None:
training = getattr(module, 'training', False) if isinstance(
module, torch.nn.Module) else False
self.train(training)
def forward(self, *args, **kwargs):
outputs = self.module(*self.convert_inputs(args, kwargs))
unflat_outputs = flat_tensors.unflattern(outputs)
return unflat_outputs我只能追到这里,self.module(*self.convert_inputs(args, kwargs)) 内部的代码就不能追了,之后outputs就为nan @chengzeyi 请问你感觉我下一步应该往哪个方向追呢 |
Author
|
我现在感觉 t5这个模块不能使用这个编译: 应该使用 类似 compile_unet 与 compile_vae 的形式 |
Author
|
抱歉猜错了,不是这个原因, 现在整个sd3 在4090上 1024*1024 大概1s,也能用,等有思路了再研究 |
生成1024x1024大小的图像,用你的代码,在3090上要7s左右。你的4090上1s左右,是做了什么优化么 |
Author
|
@ginobilinie 很久没看了, 可能是 steps 或者 显卡的影响吧 |
有可能。不知道方便加个联系方式讨论下这块么,最近在做这个。 |
|
能不能加速flux |
Author
可以的,我试过, 而且加速效果不是很明显,10%~20% 左右 |
Author
可以的 可以的 |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Uh oh!
There was an error while loading. Please reload this page.