mingti-org / phyai
PhyAI is a high-performance framework for running Physical AI models (VLA, WAM, and beyond), supporting both cloud-based serving and on-device deployment.
Why this job: matched by what the repo talks about: model, device, serv, performance
What it does
- Runs on NVIDIA Jetson edge devices
- Scales to GPU clusters with DP, TP, and CFG parallelism
- Uses high-performance kernels from FlashInfer and Humming
- Supports INT4, INT8, FP8, MXFP4, and NVFP4 quantization through kernel policies (PR under review)
Get started
git clone https://github.com/mingti-org/phyai
cd phyai
uv sync - Maintenance
- Active
- Last commit yesterday
- Stars
- 152
- +5 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- 3 releases
- None marked latest
- Built with
- Python
- 97% of the code
Is it looked after?
- Contributors
- 7
- Last 90 days
- Issues
- 19% closed
- 13 still open
- Pull requests
- 57 merged
- 13 waiting
- Releases
- 3
- 3 in the last year
- Contributing guide (opens in new tab)
- No security policy
- Code of conduct (opens in new tab)
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| baidu-baige / LoongForge | 839 | today | Apache-2.0 | No downloads |
| rokbenko / quackd | 294 | yesterday | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 97%
- C++ 2%
- Cuda <1%
- Shell <1%
Topics
- embodied-ai
- ai
- llm
- robotics
- vla
- wam
Project record
- JobLocal LLMs
- StatusListed
- Commits147
- Forks35
- Watching1
- Stars in 28 days+18
- CreatedMay 11, 2026
- First seen by usNov 7, 2026
- CheckedNov 12, 2026