Best way to learn trt and workspace question

First Question

what is the best way of learning and implementing the nature of trt with Pytorch?

Description

I set the workspace to be 2 GB. but the model uses 3.6 GB of ram when running

Environment

TensorRT Version: 8.*
GPU Type: Jetson Nano jetpack 4.6
Nvidia Driver Version:
CUDA Version: 10.2
CUDNN Version:
Operating System + Version: ubuntu
Python Version (if applicable): 3.6
TensorFlow Version (if applicable):
PyTorch Version (if applicable): 1.10.0
Baremetal or Container (if container which image + tag):

Relevant Files

Steps To Reproduce

Run trt exporter of yolov5 model. then inference with exported model

Hi,
We recommend you to check the below samples links in case of tf-trt integration issues.

If issue persist, We recommend you to reach out to Tensorflow forum.
Thanks!