-
### System Info
- CPU: X86
- GPU: NVIDIA L20
- python
- tensorrt 10.3.0
- tensorrt-cu12 10.3.0
- tensorrt-cu12-bindings 10.3.0
- tensorrt-cu12-libs 10…
-
When using keyword spotter from C-API example
Does it something internal from onnx or something we have control over?
```console
➜ sherpa-onnx git:(v1.10.28) ✗ ./build/bin/keywords-spotter-buffe…
-
Hi team, I am trying to add a custom model to TRT-LLM. The original model in PyTorch uses `torch.complex` for few tensors, in addition to FFT ops like `torch.fft.fft`, `torch.fft.ifft` and `torch.fft.…
-
您好，很高兴拜读您的代码，我有以下问题想要请教您一下
问题1：yolov8seg 您尝试过直接转int8的trt模型吗
我使用nnexec 转trt时直接报错，然而使用export代码转的trt模型又不可使用
问题2：请问您有尝试过将nms 和 seg后续处理直接放在模型内部做吗
trt模型直接 输出 box([x,y,x,y,conf,cls]) seg([nxHxW…
-
(py38) ****@ubuntu:~/*****/trt-samples-for-hackathon-cn/trtcookbook/00-Data$ python get_model_part1.py
>Traceback (most recent call last):
> File "get_model_part1.py", line 31, in
> from utils…
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and fou…
-
作者大大，你好。十分感谢您提供的从ONNX转换到TensorRT的方案，我目前遇到了一些困难
当我传入`build_engine()`的ONNX是`batch_size`为16的形式，它将会报出下面的错误
```bash
[10/30/2024-15:24:45] [TRT] [I] Found regisitered local function: stylesync_model_…
-
before operator converting, some input tensors had attributes called '_trt'
To deal wit…
-
Hello,
Thank you for this incredible project!
I was wondering if it would be possible for you to add min p sampling parameter support, it is a very useful parameter that unfortunately is not sup…
-
### System Info
colab T4
### Who can help?
@
### Information
- [X] The official example scripts
- [ ] My own modified scripts
### Tasks
- [X] An officially supported task in the `examples` fold…