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

Support SDXL and its distributed inference #1514

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Conversation

Zars19
Copy link

@Zars19 Zars19 commented Apr 28, 2024

The idea of patch parallelism comes from the CVPR 2024 paper Distrifusion. In order to reduce the difficulty of implementation, all communications in the example are synchronous.

This can help SDXL achieve better performance, especially when the resolution is very high

A100, 50 steps, 2048x2048, SDXL

Framework sync_mode n_gpu latency(s) speed_up memory(MiB)
Torch - 1 25.25 1x 42147
TRT - 1 21.98 1.15x 42895
DistrFusion(Torch) split_batch 2 13.33 1.89x 40173
Ours split_batch 2 11.69 2.16x 42675
DistrFusion(Torch) corrected_async_gn 4 8.27 3.05x 49087
DistrFusion(Torch) full_sync 4 8.64 2.92x 51943
Ours full_sync 4 7.73 3.27x 43073

@Zars19 Zars19 changed the title Add distributed inference for UNet models and SDXL examples Support SDXL and its distributed inference Apr 30, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

1 participant