TEN-framework / TEN-framework/ten-framework
TEN audio/video frame should truly leverage video memory, where lock/unlock would be real
Open
Nobody has claimed this yet.
enhancement
ten-framework
- Dominant language
- Python
- Stars
- 11.1k
- Forks
- 1.4k
- Avg merge
- 2d 15m
- Merged PRs (30d)
- 22
Description
The extra difficulty might lie in how to better ensure compatibility across different inference frameworks while minimizing copies.
Contributor guide
No contributing guide indexed for this repository
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 files, tests, or entry points are named. Start by locating the TEN audio/video frame implementation and its inference-framework boundaries, then determine how video-memory lock/unlock should work while minimizing copies. Done means a defined, compatible approach that truly leverages video memory across the relevant frameworks.
Written by the indexing model from the issue text.
Assessment
- Domain
- audio-video-rtc, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100