NVIDIA / NVIDIA/TensorRT-Model-Connect
Feature: Visibility tools for perf optimization and debugging
Open
Nobody has claimed this yet.
enhancement
New Feature Request
- Dominant language
- Python
- Stars
- 254
- Forks
- 58
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 235
Description
Request type
New model or checkpoint support
Problem and use case
Improve user visibility for following scenarios:
- perf optimization. e.g. ONNX preview, user/devTech is able to find perf optimization opportunities through ONNX viz tool
- debugging for accuracy
the viz scenarios might be expended in the future
Proposed outcome
viz tool is enabled
could integrate with the existing NV profiling tools like NDLD
Model and target details
No response
Alternatives considered
No response
Additional context
No response
Submission checks
- I searched open and closed issues and found no duplicate request.
- I removed secrets, private/internal evidence, personal paths, and restricted artifacts.
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 file, test, model, or checkpoint is named. Start by locating the repository's existing model-support and profiling entry points, then determine how ONNX visualization and accuracy-debugging workflows fit there. Done means the visualization tool is enabled for a defined target, with any NDLD integration explicitly scoped.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- devtools, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 28/100