Running onnxruntime with a gpu in nodejs?

Nobody has claimed this yet.

### Describe the issue

Hello!

I'm trying to run yolov7 in nodejs but I am getting poor performance as it is using my cpu instead of my gpu.
Onnxruntime-web mentions the capability of using nodejs and gpu but when requiring it in node.js I get "Uncaught Error Error"
How would I get onnxruntime-node to run on my gpu for better performance?

Thanks!

### To reproduce

I'm using yolov7-w6-pose-nms.onnx from https://github.com/trancongman276/yolov7-pose

### Urgency

_No response_

### Platform

Windows

### OS Version

Windows 10

### ONNX Runtime Installation

Released Package

### ONNX Runtime Version or Commit ID

onnxruntime-node@1.13.1

### ONNX Runtime API

JavaScript

### Architecture

X64

### Execution Provider

CUDA

### Execution Provider Library Version

_No response_

Start by reproducing the issue on Windows 10 with onnxruntime-node@1.13.1, the yolov7-w6-pose-nms.onnx model, and the CUDA execution provider. Check why the Node.js package reports an error and uses the CPU; done means inference runs through the GPU, but the issue does not name a repository file or test to guide the investigation.

Written by the indexing model from the issue text.