Laugh

@zgkom @duskkkrua @KeyKy @0x3878f 找到解决方法了，属实难绷。 就得执行这条指令：`python -m pip install --pre paddlepaddle-gpu==3.0.0.dev20250426 -i https://www.paddlepaddle.org.cn/packages/nightly/cu126/`，装 `3.0.0.dev20250426` 这个开发版的 PaddlePaddle ，没别的招。 说真的，正常人谁会去装开发版啊（明明开发版该不稳定，结果这次正式版才是真·不稳定）？ 要导出 PPOCRv5 ，PaddlePaddle 版本就必须是 3.0+，正常安装 Paddle2ONNX 导出，会直接报`ImportError: DLL load failed while importing...

@LynnGuo666 @limbo1996 我这边修复了 https://github.com/nilaoda/BBDown/pull/1037

@levipereira I attempted to build [TensorRT release 8.6](https://github.com/levipereira/TensorRT/tree/release/8.6) and [TensorRT release 10.0](https://github.com/levipereira/TensorRT/tree/release/10.0), and also built the EfficientNMSX-related code on the 10.1 and 10.2 branches of [NVIDIA TensorRT](https://github.com/NVIDIA/TensorRT). When building and...

@andrew-93, you might want to try building TensorRT on a different device. I’ve tested it on the 2080 Ti, 3060 Ti, and 4090, and only the 2080 Ti is not...

> 我建议尝试不同的工作空间大小，例如 4GB 和 20GB，看看问题是否仍然存在。Efficient_NMS插件也可能会出现此问题，因此检查此内容可以提供额外的见解。 > > 我有一台 RTX 2060/2070，我会尽快测试。 ```sh [08/07/2024-07:53:41] [I] === Model Options === [08/07/2024-07:53:41] [I] Format: ONNX [08/07/2024-07:53:41] [I] Model: D:\laugh\Projects\TensorRT-YOLO\demo\obb\models\yolov8s-obb.onnx [08/07/2024-07:53:41] [I] Output: [08/07/2024-07:53:41] [I]...

@ttyio The issue still occurs on different devices using both v10.0.1.6 and v8.6.1 versions.

@jdbsid @NghiaKTHP Reslove https://github.com/PaddlePaddle/Paddle2ONNX/issues/1570#issuecomment-3514690785