NVIDIA / NVIDIA/TensorRT

The same engine produces incorrect inference output using C++, but correct results using Python. TensorRT-8.6.1.6+cuda12.1

Open
#3,617 8 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

TensorRT-8.6.1.6+cuda12.1
GPU RTX3090 24G

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

No source files, tests, model, or reproducible inputs are identified. Start by collecting a minimal reproduction that compares the C++ and Python TensorRT 8.6.1.6 inference paths on CUDA 12.1 and the RTX 3090, including model outputs and build details. Done means the discrepancy is reproduced and its cause is isolated or documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
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.