] Error Code 1: Myelin (autotuning: CUDA error 3 allocating 0-byte buffer: )

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

I got this error on an ONNX model which works perfect on TensorRT 7

After upgrade to tensorrt 8.0 or tensorrt 8.2, always hit this error.

my model is DETR a transformer oNNX model which can be accessed from facebookresearch repo.

2

Hi @LucasJin , welcome back to the NVIDIA Developer forums!

Judging from how you describe your issue being connected to TensorRT, I moved this topic to that specific category

I hope you will get it resolved soon.

Markus

3

Thank you @MarkusHoHo.

4

Hi @LucasJin,

Could you please share us issue repro ONNX model and trtexec --verbose logs for better help.

Thank you.

5

Hi,
Request you to share the ONNX model and the script if not shared already so that we can assist you better.
Alongside you can try few things:

  1. validating your model with the below snippet

check_model.py

import sys
import onnx
filename = yourONNXmodel
model = onnx.load(filename)
onnx.checker.check_model(model).
2) Try running your model with trtexec command.
https://github.com/NVIDIA/TensorRT/tree/master/samples/opensource/trtexec
In case you are still facing issue, request you to share the trtexec “”–verbose"" log for further debugging
Thanks!

7

Oh, after serveral years I just got the message.
However, seems I have already made DETR inference via tensorrt long time ago.