How to close part of fusions in TensorRT 10.16
Open
Nobody has claimed this yet.
Module:ONNX
- Dominant language
- C++
- Stars
- 13.4k
- Forks
- 2.4k
- Avg merge
- 5d 3h
- Merged PRs (30d)
- 2
Description
I experienced a precision issue during the ONNX to TRT conversion of DEIMv2. The final outputs are correct when all nodes' outputs are printed, so I need to turn off layer fusion during the conversion to ensure the accuracy. Is there any way to control this?
The problem is described in https://github.com/Intellindust-AI-Lab/DEIMv2/issues/152
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the ONNX-to-TensorRT conversion described in the issue and review the linked DEIMv2 issue 152. Determine whether TensorRT 10.16 exposes control over only the affected fusions; done means establishing a reproducible way to preserve correct outputs without printing every node.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- 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