TensorRT

TensorRT copied to clipboard

load .trt file built by trtexec to create an engine by running engine = runtime->deserializeCudaEngine(), but get null

2

I use trtexec to build an engine file, and try to load it by ifstream(name,std::ios::binary), but got null engine. what should Ido?

Fuzhiyuan

[Feature request] Make using incompatible timing caches for building CUDA engines not a hard error

1

## Description I am currently researching ways for speeding up building TensorRT's CUDA engines in the runtime from ONNX models using the C++ API. That is, I am loading the...

dev0x13

Allocating TensorRT model on GPU consumes all available Memory

1

## Description When I llocate a TensorRT model on GPU it consumes all available memory on the device. I have tried instantiating the model with an empty GPU and with...

sam-h-bean

The docstring of Python class tensorrt.IBuilderConfig.algorithm_selector is miss

2

## Description ## Environment **TensorRT Version**: 8.4.1 **NVIDIA GPU**: **NVIDIA Driver Version**: **CUDA Version**: **CUDNN Version**: **Operating System**: **Python Version (if applicable)**: **Tensorflow Version (if applicable)**: **PyTorch Version (if applicable)**:...

gzpan

When run "python -m pip install colored polygraphy --extra-index-url https://pypi.ngc.nvidia.com", Can`t find install.ps1

4

Fuzhiyuan

How to add QDQ before LeakyRelu

1

## Description ## Environment **TensorRT Version 8.4: **NVIDIA GPU p40: **NVIDIA Driver Version 470: **CUDA Version 11.0: **CUDNN Version 8.1: **Operating System linux: **Python Version (if applicable) 3.6: **Tensorflow Version...

pangr

addFullyConnected will be replaced by addMatrixMultiply + addElementWise?

1

## Description ## Environment **TensorRT Version**: **NVIDIA GPU**: **NVIDIA Driver Version**: **CUDA Version**: **CUDNN Version**: **Operating System**: **Python Version (if applicable)**: **Tensorflow Version (if applicable)**: **PyTorch Version (if applicable)**: **Baremetal...

zhoutianzi666

why 7234 和 8406 diffs in layer's output dimensions when constructing network

3

## Description ## Environment **TensorRT Version**: **NVIDIA GPU**: **NVIDIA Driver Version**: **CUDA Version**: **CUDNN Version**: **Operating System**: **Python Version (if applicable)**: **Tensorflow Version (if applicable)**: **PyTorch Version (if applicable)**: **Baremetal...

zhoutianzi666

Create onnx graph throws AttributeError: 'Variable' object has no attribute 'values'

8

# Problem description Hi All, I am trying to build a TensorRT engine from TF2 Object detection API SSD MobileNet v2 320x320. I followed https://github.com/NVIDIA/TensorRT/tree/main/samples/python/tensorflow_object_detection_api I successfully exported the TensorFlow...

SEHAIRIKamal

Does TensoRT support the fusion of leayrelu and conv?

6

pangr