paster
May 19, 2021, 10:54am
1
Description
Hello,
running the next code:
python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images/
on A100 GPU is giving the next error: "RunTimeError: CUDA error: no kernel is availible for execution on the drive.
the running the same conda environment & the same python command & the same OS on RTX 5000 GPU is succesfull.
What is the reson for failure in A100?
Thank you.
Inga
Environment
TensorRT Version :
GPU Type : A100-PCIE-40GB
Nvidia Driver Version : 450.51.06
CUDA Version : 11.0
CUDNN Version :
Operating System + Version : Red Hat Enterprise Linux release 8.3
Python Version (if applicable) : 3.9.1
TensorFlow Version (if applicable) : N/A
PyTorch Version (if applicable) : torch → 1.8.1, torchvision → 0.9.1
Baremetal or Container (if container which image + tag) : N/A
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 19, 2021, 11:08am
2
Hi ,
We recommend you to check the supported features from the below link.
These support matrices provide a look into the supported platforms, features, and hardware capabilities of the NVIDIA TensorRT 8.4.3 APIs, parsers, and layers.
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
<!--- 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!
Hi @paster ,
This forum talks more about updates and issues related to TensorRT. We request you to post your concern on pytorch related platform to get better help.
May be this will help you.
Thank you.