pytorch "scatter_add_ " not work failure of TensorRT 8.6.1.6 when running tensorRT model
Open
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
the code is line
tensor.scatter_add_(2, idx[:, :, k, :], input[:, :, k, :])
onnx convert to tensorrt success no error reported，when i runing the tensorrt model, the result is wrong,i investigate the scatter_add_ not work。
### Tasks
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
No repository file or test is identified. Start by reproducing the reported tensor.scatter_add_ case with the provided indexing expression, ONNX conversion, and TensorRT 8.6.1.6, then compare the TensorRT output with the source model. Done means the discrepancy is isolated and either fixed or documented with a minimal reproducer.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100