-
Notifications
You must be signed in to change notification settings - Fork 130
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
Speed Question #227
Comments
Hi, can you provide more details about how you run the code? And do your H100 have nvlink? |
I copy the pab_mgr.py comm.py parallel_mgr.py files and open_sora_transformer_3d.py, and then use the command :torchrun --nproc_per_node 8 scripts/inference_pab.py configs/opensora-v1-2/inference/sample.py |
my configuration parameter of pab is defalt |
I use DSP too |
and i wonder why your sample speed is so fast,192frames 480p noly 94s, is my H100's problem? |
Hi, would you mind indicate which script you are using? VideoSys is currently using a builtin multi-processing launcher. Therefore elastic launch with torchrun is not recommended. |
why 8H100's acceleration effect is very small, but single H100's acceleration effect is complied with the article
I test with 512 * 512, 51 frames
without pab(1H100):157.61683344841003s
with pab(1H100):136.60238338s
with pab(8H100):106.87562332s
The text was updated successfully, but these errors were encountered: