pegainfer-project / kern
A model-agnostic GPU runtime for shipping models as verified programs.
Why this job: matched by what the repo talks about: model, gpu, runtime, verifi
What it does
Today's engines are million-line programs that carry, in one codebase:
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit yesterday
- Stars
- 187
- +27 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- Linux
- From the latest release
- Latest version
- v0.4.0
- Released 6 days ago
- Built with
- Rust
- 70% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 38% closed
- 13 still open
- Pull requests
- 83 merged
- 9 waiting
- Releases
- 8
- 9 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| brontoguana / krasis | 529 | 4 days ago | Custom | Windows, Linux |
| liguodongiot / llm-action | 25,274 | 29 days ago | Apache-2.0 | No downloads |
| flashinfer-ai / flashinfer | 6,900 | today | Apache-2.0 | Linux |
More: download files, languages, topics and project record
Languages
- Rust 70%
- Python 18%
- Cuda 5%
- TypeScript 3%
Topics
- cuda
- gpu-inference
- llm-inference
- rust
Project record
- JobLocal LLMs
- StatusListed
- Commits364
- Forks12
- Watching0
- Stars in 28 days+94
- CreatedAug 29, 2026
- First seen by usNov 7, 2026
- CheckedNov 12, 2026