You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I get this error: "RuntimeError: Detected that you are using FX to torch.jit.trace a dynamo-optimized function. This is not supported at the moment."
Could you please advise if there is any solution to resolve this? Thanks
The text was updated successfully, but these errors were encountered:
Hi,
I'm calculating flops for open-sora model with backbone of STDiT and three inputs: x, timestamp, and y, like the following:
from fvcore.nn import FlopCountAnalysis
flops = FlopCountAnalysis(model, (x, torch.randint(0, 10, (x.shape[0],), device=x.device), model_args['y']))
flops.total()
I get this error: "RuntimeError: Detected that you are using FX to torch.jit.trace a dynamo-optimized function. This is not supported at the moment."
Could you please advise if there is any solution to resolve this? Thanks
The text was updated successfully, but these errors were encountered: