Excluding the model loading time, how long does inference take on T4 GPU? #128

Closed
opened 2023-09-28 16:20:10 +02:00 by DaeseungLee · 1 comment
DaeseungLee commented 2023-09-28 16:20:10 +02:00 (Migrated from github.com)

Hello!

I want to optimize inference time.
How long does inference take on T4 GPU for single image?

I takes 14 seconds excluding loading model.
There are any technique to reduce the time?

Thanks!

Hello! I want to optimize inference time. How long does inference take on T4 GPU for single image? I takes 14 seconds excluding loading model. There are any technique to reduce the time? Thanks!
glucauze commented 2023-10-04 10:35:57 +02:00 (Migrated from github.com)

Did you check GPU is really used and CUDA provider is selected ? It should be enabled on settings too. That's surprisingly slow. Without upscaling it should be less than 2s. It is the case on my RTX3080ti. I don't have experience with T4. I will check on a M40 if i have time.

Did you check GPU is really used and CUDA provider is selected ? It should be enabled on settings too. That's surprisingly slow. Without upscaling it should be less than 2s. It is the case on my RTX3080ti. I don't have experience with T4. I will check on a M40 if i have time.
Sign in to join this conversation.