NVIDIA / NVIDIA/TensorRT

core dump in bart trt engine

Open
#1,793 10 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

triaged
Dominant language
C++
Stars
13.4k
Forks
2.4k
Avg merge
5d 3h
Merged PRs (30d)
2

Description

Description

when i use trtexec to generate bart trt engine, there is core dump.

image

Environment

TensorRT Version: 8.2.1
NVIDIA GPU: T4
NVIDIA Driver Version: 470.82.01
CUDA Version: 11.5.50
CUDNN Version:
Operating System: Ubuntu 20.04.3 LTS
Python Version (if applicable): 3.8.10
Tensorflow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if so, version):
onnx 1.7.0
onnx-graphsurgeon 0.3.14
onnxruntime 1.8.0
onnxruntime-gpu 1.8.0

Relevant Files

Steps To Reproduce

https://github.com/huggingface/transformers/tree/v4.15.0/examples/onnx/pytorch/summarization
1.python run_onnx_exporter.py --model_name_or_path facebook/bart-base
2.trtexec --onnx=BART.onnx --workspace=64 --minShapes=input_ids:1x1 --optShapes=input_ids:1x32 --maxShapes=input_ids:1x64 --buildOnly --saveEngine=test.engine

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the crash with run_onnx_exporter.py and the supplied trtexec command using BART.onnx in the listed TensorRT, CUDA, driver, and Ubuntu environment. Capture the core-dump stack and trace it through the relevant TensorRT or trtexec entry point; done means the same command builds test.engine without a core dump.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp, python
Domain
machine-learning, tooling
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.