Description
Hi!
I run yolo11 model inference for 1000 times in Tesla T4, but I found the time cost was very unstable.
From the cached records, I found most of the time costs were even and looked normal, but there always existed a few abnormal ones. For example, of the 1000 times inference records, most of the inference time cost was 2ms per image, but there were a few that cost 70ms per image.
I had tried to set a fixed card frequency but it didnt seem to work.
So can you help me with that? Thanks!
Environment
TensorRT Version: 10.6.0.26
GPU Type: Tesla T4
Nvidia Driver Version: 565.57.01
CUDA Version: 12.6
CUDNN Version: 9
Operating System + Version: ubuntu 22.04
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):
Relevant Files
I think this is probbably something to do with card configuration, rather than my code, so not provide first.