TensorRT

TensorRT copied to clipboard

## Description Hello! I have a pipeline, that gets TRT engine from a torch checkpoint, which works fine for Cuda11.4 && TensorRT-7.2.3.4-1.cuda11.1. When I tried to upgrade GPU libs (and...

Beshkent

Jetson Nano : Error TensorRT : Error Code 10: Internal Error (Could not find any implementation for node StatefulPartitionedCall/ArgMax.)

4

Hello, After compiling tensorRT 8.4.2 from source, and try to convert my onnx model to TRT model on my jetson nano I got the following error : > Internal Error...

AlexandreBourrieau

ERROR: Could not build wheels for tensorrt, which is required to install pyproject.toml-based projects

2

## Description Getting this error ''' ``` Collecting tensorrt Using cached tensorrt-8.6.1.post1.tar.gz (18 kB) Preparing metadata (setup.py) ... done Building wheels for collected packages: tensorrt Building wheel for tensorrt (setup.py)...

KaifAhmad1

result verify failure of TensorRT 8.5.10 when converting onnx model to trt model

5

## Description I have trained a tensorflow model and converted it into onnx modesl and trt models, but the results of these two models can totally not match. I use...

ForMerLen

7.1.3 aarch64 tar file missing from https://developer.nvidia.com/nvidia-tensorrt-7x-download

1

## Description Hi! https://docs.nvidia.com/deeplearning/tensorrt/archives/tensorrt-713/support-matrix/index.html lists aarch64 as a supported platform for 7.1.3. Yet, there seems to be no relevant tar file for it in the nvidia developer zone https://github.com/NVIDIA/TensorRT/tree/release/7.1. Your...

ethan-hindes

Are torch.nn.functional methods automatically quantized by pytorch-quantization?

4

## Description I am trying to quantize a Pytorch model to INT8 to run with tensrorrt. I have read these [docs](https://docs.nvidia.com/deeplearning/tensorrt/pytorch-quantization-toolkit/docs/index.html), and am still unclear on whether I have to...

AndyWanna

Internal Error (/lightglue/ArgMax)

11

When I run the model with TensorRT 8.6.2 and CUDA 12.2 in Jetson Device, there are a lot of errors: (Ubuntu 22.04, Jack Pack 6.0 R36.2 https://developer.nvidia.com/embedded/jetpack#collapseAllJetson ) [E] [TRT]...

chenscottus

Segmentation fault for TensorRT 8.6 when loading ONNX model via C++ API on GPU V100

1

## Description I tried to use the C++ API to load the attached ONNX model but it fails with a segmentation fault (core dumped). Note: possibly related to https://github.com/NVIDIA/TensorRT/issues/3630, this...

lhai37

NVRTC failure of TensorRT 8.4.0 when running trtexec generate engine of PETR.engine(autonomous driving 3D object detection algorithm:PETR)on GPURTX3070

3

NVRTC Compilation failure Aborted (core dumped) how to solve this problem?(attachment is log of engine) [Uploading log_3070.json…]() /usr/bin/trtexec \ --onnx=petr.onnx \ --saveEngine=petr.trt \ --fp16 \ --inputIOFormats=fp32:chw \ --outputIOFormats=fp16:chw \ --verbose...

wutheringcoo

"This version of TensorRT does not support dynamic axes." failure of TensorRT 8.5.2 and 8.6.1 when running groundingdino.onnx on GPU Tesla V100 and Tesla T4

9

## Description I tried to convert grouding.onnx to tensorrt on GPU, but it fails with the error below torch2onnx commend: ``` caption = "the running dog ." #". ".join(input_text) input_ids...

Qia98