ekzhang / resin
🧱 Experimental library for building inference engines
Why this job: topics: inference, llm-serving
What it does
- Parallelisms. TP, EP, CP, and DP Attention
- Prefill and decode CUDA graphs
- Native renderer and incremental parser
- NUMA pinning on worker startup
Get started
pip install "git+https://github.com/ekzhang/resin.git" - Maintenance
- Active
- Last commit 4 days ago
- Stars
- 422
- +45 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 73% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 67% closed
- 2 still open
- Pull requests
- 25 merged
- 1 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| vllm-project / vllm | 96,588 | today | Apache-2.0 | Mac, Linux |
| thu-pacman / chitu | 3,000 | 2 days ago | Apache-2.0 | No downloads |
| SemiAnalysisAI / InferenceX | 2,010 | today | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 73%
- Rust 24%
- Jinja 1%
- HTML 1%
Topics
- inference
- llm
- cuda
- gpt-oss
- inkling
- llm-serving
- deepseek
- gpu
Project record
- JobLocal LLMs
- StatusListed
- Commits504
- Forks31
- Watching3
- Stars in 28 days+422
- CreatedAug 8, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026