用 C++ 与 NVIDIA TensorRT RTX 构建本地 AI 应用
原标题：Build Local AI Apps with C++ and NVIDIA TensorRT RTX Samples
AI 摘要
NVIDIA 在技术博客中介绍了开源项目 DIN Deploy，它提供一套 C++ 示例，结合 ONNX Runtime 与 NVIDIA TensorRT RTX 执行提供程序，帮助开发者将 Hugging Face 模型检查点导出为 ONNX 并在 Windows、Linux 上构建本地硬件加速应用。示例覆盖 Whisper、Parakeet、Nemotron ASR 流式识别、Meta SAM 2.1 分割以及 FLUX.2 图像生成，并给出 DGX Spark 上 GPU 相对 CPU 的加速数据。项目还演示了通过 NVIDIA Model Optimizer 进行训练后量化，量化模型可无代码改动直接替换。
正文节选
Adding AI models to local applications requires a portable model format, a reliable runtime, and acceleration that works across target systems. Do Inference Now (DIN) Deploy is an open-source collection of practical C++ samples that bridges that gap. It combines ONNX Runtime with the NVIDIA TensorRT RTX execution provider to help developers move from a model checkpoint to a native, hardware-accelerated application on Windows and Linux. The same ONNX Runtime API can also be accessed through WinML