Store the converted TensorRT engine and context so can be loaded and used faster next time
Open
Nobody has claimed this yet.
Feature Request
- Dominant language
- C++
- Stars
- 13.4k
- Forks
- 2.4k
- Avg merge
- 5d 3h
- Merged PRs (30d)
- 2
Description
Hi!
May I kindly ask if there are APIs to store the engine and context created by tensorRT in some files (just like how we can store ONNX models in a .onnx file), so that it can be loaded and used faster next time?
Thank you!
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, or entry point is named. First determine whether TensorRT already exposes serialization for the engine and context, then define the requested API and a reproducible loading-speed test; the issue does not establish clear completion criteria.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100