Inference time is longer than training time

[Qusijia]

My training time is much shorter than my reasoning time. Would you like to inquire if this situation is normal? Or what advice can you give me.

Training Code：
loss = priorTrainer.diffusion_prior(text_embed=text_embed, image_embed=image_embed, text_encodings=None)
priorTrainer.optimizer.zero_grad()
loss.backward()
priorTrainer.optimizer.step()
priorTrainer.scheduler.step()

Inference code：
prior.sample_add( text_embed = text_embed)

[AIDevMonster]

sorry, I'm busy now.
2 days late, I will send you.
thx.
Paul