Develop tensorrt sam faster model inference

[Yakuho]

Motivation and context

Improve SAMEncoder inference speed for interactor mode

How has this been tested?

Test condition: GPU: RTX-3090, CPU: Intel(R) Xeon(R) Gold 6248R CPU @ 3.00GHz, pytorch-cu121==2.5.1,
tensorrt-cu12==10.6.0, onnx==1.20.1, onnxsim==0.4.36

exported onnx model version: opset_version==18, dtype==float32

/	pth	trt
gpu-memory	~7000m	~7000m
speed	~420ms	~250ms

totally, trt will bring about a 40% improvement

Checklist

• I submit my changes into the develop branch
• I have created a changelog fragment
• I have updated the documentation accordingly
• I have added tests to cover my changes
• I have linked related issues (see GitHub docs)

License

• I submit my code changes under the same MIT License that covers the project.
  Feel free to contact the maintainers if that's a concern.

[sonarqubecloud]

Quality Gate passed

Issues
14 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube Cloud