A10 card cannot be found by nvidia-smi

865463381 · May 24, 2021, 3:04am

Description

I have an A10 card for deep learning, I installed the NVIDIA-Linux-x86_64-460.73.01.run driver.
I also installed a T4 card on the same machine. So now these two cards are simultaneously installed on this machine.
When I type nvidia-smi ,only T4 card appear.

Environment

TensorRT Version:
GPU Type: NVIDIA A10, Tesla T4
Nvidia Driver Version: NVIDIA-Linux-x86_64-460.73.01.run
CUDA Version:
CUDNN Version:
Operating System + Version: CentOS 7
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

Exact steps/commands to build your repro
Exact steps/commands to run your repro
Full traceback of errors encountered

NVES · May 24, 2021, 3:07am

Hi ,
We recommend you to check the supported features from the below link.

You can refer below link for all the supported operators list.
For unsupported operators, you need to create a custom plugin to support the operation

github.com

onnx/onnx-tensorrt/blob/main/docs/operators.md

<!--- SPDX-License-Identifier: Apache-2.0 -->

# Supported ONNX Operators

TensorRT 8.4 supports operators up to Opset 17. Latest information of ONNX operators can be found [here](https://github.com/onnx/onnx/blob/master/docs/Operators.md)

TensorRT supports the following ONNX data types: DOUBLE, FLOAT32, FLOAT16, INT8, and BOOL

> Note: There is limited support for INT32, INT64, and DOUBLE types. TensorRT will attempt to cast down INT64 to INT32 and DOUBLE down to FLOAT, clamping values to `+-INT_MAX` or `+-FLT_MAX` if necessary.

See below for the support matrix of ONNX operators in ONNX-TensorRT.

## Operator Support Matrix

| Operator                  | Supported  | Supported Types | Restrictions                                                                                                           |
|---------------------------|------------|-----------------|------------------------------------------------------------------------------------------------------------------------|
| Abs                       | Y          | FP32, FP16, INT32 |
| Acos                      | Y          | FP32, FP16 |
| Acosh                     | Y          | FP32, FP16 |
| Add                       | Y          | FP32, FP16, INT32 |

This file has been truncated. show original

Thanks!

865463381 · May 24, 2021, 3:13am

I think it’s no relation to my question…

spolisetty · May 24, 2021, 10:14am

Hi @865463381,

This forum talks more about updates and issues related to TensorRT. We recommend you to please post your concern on related platform.
You may get better help here.

Thank you.

Topic		Replies	Views
nVidia release versions compatibility TensorRT	4	1050	September 20, 2023
Does TensorRT support GeForce and Quadro boards TensorRT	1	696	April 6, 2023
TensorRT, result error in fp16 TensorRT	1	709	October 19, 2021
TensorRT version for CUDA 12.0 TensorRT tensorrt , cuda	1	1848	March 14, 2023
Unable to use TensorRT 7.2.3 for Ubuntu 18.04 and CUDA 11.2 TensorRT	6	4567	May 6, 2021
Comaptibility Of TensorRT with Windows 11 Professional TensorRT	2	2323	December 6, 2021
After removing Tensorrt, can't install anything NVIDIA TensorRT cudnn	0	390	December 20, 2023
Detectron2 needs Cuda max 11.3 Version TensorRT	1	2053	March 10, 2022
TensorRT 8.2 + CUDA 11.4 -> which CuDNN version? TensorRT	6	3332	November 24, 2021
Tensorrt 8.0.0.3 with cuda 11.1 TensorRT tensorrt	2	1655	August 28, 2021

A10 card cannot be found by nvidia-smi

Description

Environment

Relevant Files

Steps To Reproduce

Related topics