NVIDIA / NVIDIA/TensorRT

engine build problem

Open
#4,730 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

I am using TensorRT 10.8 on the Thor-U. When building an engine with trtexec and performing inference, I noticed that running the same command with the same parameters multiple times can produce two different engine graphs, which leads to different inference results.

Is it expected that engine builds are inconsistent even when using identical commands and parameters?

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

The issue names no source files, tests, or entry points. Start by reproducing the exact trtexec command on Thor-U with TensorRT 10.8, then compare the generated engine graphs and inference outputs across repeated builds. Done means determining whether the differences are expected and documenting the cause or a reproducible defect.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.