v0.1.0: First release

[2024.03.08] First release v0.1.0 on March 8, 2024:

Enables rapid deployment of various deep learning models, converting them into TensorRT engine files.
Supports multi-precision model deployment, including int8 quantization, with fine-tuning capabilities during quantization.
Supports Quantization-Dequantization (QDQ) for quantizing ONNX models.
Facilitates model inference accuracy validation across multiple platforms (PyTorch, ONNXRuntime, TensorRT).
Includes support for the Efficient NMS plugin, Rotated Object Detection NMS plugin, and YOLO decode plugin.