search

NVIDIA / TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
https://developer.nvidia.com/tensorrt
Apache License 2.0
10.56k stars 2.1k forks source link

NVMAP_IOC_PARAMETERS failed of TensorRT 8.5 when running on Orin #3530

Closed distant1219 closed 8 months ago

distant1219 commented 9 months ago

Description

when I run a DLA model in orin, it occured when code exited. image I don't know what meaning is and how effect for other code.

Environment

TensorRT Version: 8.5.2

NVIDIA GPU:Jetson AGX Orin NVIDIA Driver Version:

CUDA Version: 11.4

CUDNN Version: 8.4.1

Operating System:

Python Version (if applicable):

Tensorflow Version (if applicable):

PyTorch Version (if applicable):

Baremetal or Container (if so, version):

Relevant Files

Model link:

Steps To Reproduce

Commands or scripts:

Have you tried the latest release?:

Can this model run on other frameworks? For example run ONNX model with ONNXRuntime (polygraphy run <model.onnx> --onnxrt):

zerollzeng commented 9 months ago

Checking internally. But this won't affect the program, right?

zerollzeng commented 9 months ago

I also saw this few times but didn't pay much attention to it.

distant1219 commented 9 months ago

When I use trtexec to run this engine plan, this bug happened again.

zerollzeng commented 9 months ago

Could you please try latest 6.0.8/6.0.9 release? Thanks!

ttyio commented 8 months ago

closing since no activity for more than 3 weeks, pls reopen if you still have question, thanks!