TensorRT

TensorRT copied to clipboard

How to implement a tensorrt plugin for "Unique" op?

1

I want to implement a plug-in for the operator Unique. But I don’t know how to determine its output dimension, because it cannot be determined directly based on the input...

BobLiu20

onnx_graphsurgeon: fix Sequence Tensor bug

3

Hi, when using graphsurgeon to handle model with [SequenceConstruct](https://onnx.ai/onnx/operators/onnx__SequenceConstruct.html) operator, constant folding will raise an error, this pr helps fix it, model is provided [model.zip](https://github.com/NVIDIA/TensorRT/files/14035970/model.zip). current output after constant folding...

inisis

LayerNormalization failure of TensorRT 8.2.4.2

3

## Description Does 8.2.4.2 support LayerNormalization? With the same onnx model and conversion instructions, I successfully converted on 8.6.1.6, but not on 8.2.4.2. But I have to adapt to the...

lin-lcx

RT-DETR FP16 inference get correct result on v100 but weird result on a10

2

## Description I am using tritonserver:23.10 to deploy RT-DETR model. The onnxruntime fp32, onnxruntime fp16 and Tesla V100 TRT 8.6.1 FP16/F32 both get the correct result. But Tesla A10 TRT...

xiaochus

`ScatterElements` with Reduction (opset 16) Not Fully Supported

1

## Short Description Conversion of an ONNX model to TensorRT using `trtexec`, which includes a `scatterElements` operation with a reduction like `"sum"` (opset 16), fails when the number of indices...

anthony-correia

Unable to load library: nvinfer_builder_resource.dll failure of TensorRT 8.6 when running assert tensorrt.Builder(tensorrt.Logger()) on GPU NVIDIA GeForce RTX 4060

4

## Description I installed TensorRT and CUDNN on Windows for using with yoloV8. Following nvidia documentation (zip installation): [TensorRT installation documentation](https://docs.nvidia.com/deeplearning/tensorrt/archives/tensorrt-861/install-guide/index.html#installing-zip) But when I ran this code on Python3.11: ```...

sujonahmed2500

trtexec failure of TensorRT 8.6.1.6 when running trtexec on GPU RTX4090

6

## Environment **TensorRT Version**: **NVIDIA GPU**: RTX 4090 **NVIDIA Driver Version**: 535.129.03 **CUDA Version**: 11.8 **CUDNN Version**: 8.9.6.50 Operating System: ubuntu 22.04 Python Version (if applicable): 3.9 Tensorflow Version (if...

peter5232

how to add_ElementWise with two dynamic shape tensor

2

example: both a and b with shape (8, 1, 1, -1), how to add a and b. can anyone tell me Thanks!

dawenxi-only

TensorRT v9.2 installation error due to CUDA version. ""-- The CUDA compiler identification is unknown""

1

Hello everyone, I'm trying to install TensorRT version 9.2. I followed the requirements and switched to CUDA 12.2 on a 16GB GPU machine running Ubuntu 20. When I run the...

jamil-z

i have some problems about my work, when i use tensorRT to convert file pt to file.wts and this step $ sudo ./yolov7 -s yolov7-tiny.wts yolov7-tiny.engine t, i meet this problems, can i help me, please....

3

jetson@duongphiv5-desktop:~/JetsonYOLOv7-TensorRT/yolov7/build$ sudo ./yolov7 -s yolov7-tiny.engine t Using engine, please wait for a while... weights: yolov7-tiny.wts ... [02/24/2023-13:22:21] [E] [TRT] (Unnamed Layer* 187) [Convolution]: kernel weights has count 648 but 5760...

Phi22323