Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[stable diffusion] [unet] [compiling] faild to find implemtation ForeignNode[/up_blocks.0/resnets.0/time_mixer/Constant_1_output_0.../conv_act/Mul #4360

Open
focusunsink opened this issue Feb 19, 2025 · 7 comments
Assignees
Labels
Module:DemoDiffusion Issues regarding demoDiffusion question Further information is requested triaged Issue has been triaged by maintainers

Comments

@focusunsink
Copy link

No description provided.

@focusunsink focusunsink changed the title faild to find implemtation ForeignNode[/up_blocks.0/resnets.0/time_mixer/Constant_1_output_0.../conv_act/Mul [stable diffusion] [unet] [compiling] faild to find implemtation ForeignNode[/up_blocks.0/resnets.0/time_mixer/Constant_1_output_0.../conv_act/Mul Feb 19, 2025
@focusunsink
Copy link
Author

GPU: 4090 or H800.
tensorrt 10.6.0
torch 2.4.0

when I compile unet using tensorrt. it raise this error. Even I use H800 to make more memory available. This error still happens.

@focusunsink
Copy link
Author

This is because image is to large or frames is too many. when I change frames from 72 to 16. it success.

@kevinch-nv kevinch-nv added question Further information is requested triaged Issue has been triaged by maintainers Module:DemoDiffusion Issues regarding demoDiffusion labels Mar 7, 2025
@kevinch-nv
Copy link
Collaborator

@asfiyab-nvidia perhaps it'll be useful to provide a table denoting VRAM requirements for different pipelines in the README

@focusunsink
Copy link
Author

This could be avoided when I set config.num_tactics = 2 or other small number. So search tactics may consume much VRAM

@asfiyab-nvidia
Copy link
Collaborator

@kevinch-nv sounds good. We can release VRAM documentation for pipelines in the next release.
@focusunsink have you tried lowering the builder optimization level using the --optimization_level flag? The default value is 3 for most pipelines. You can reduce it for further memory savings

@focusunsink
Copy link
Author

I set config.builder_optimization_level = 3, still not work.

@focusunsink
Copy link
Author

I set workspace=8
config.set_memory_pool_limit(trt.MemoryPoolType.WORKSPACE, workspace << 30)
then it works

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Module:DemoDiffusion Issues regarding demoDiffusion question Further information is requested triaged Issue has been triaged by maintainers
Projects
None yet
Development

No branches or pull requests

3 participants