fastmachinelearning / qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
Why this job: topics: inference, quantization
What it does
QONNX (Quantized ONNX) introduces several custom operators -- IntQuant, FloatQuant, BipolarQuant, and Trunc -- in order to represent arbitrary-precision integer and minifloat quantization in ONNX. This enables:
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 months ago
- Stars
- 195
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.0.0
- Released 8 months ago
- Built with
- Python
- 89% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 43% closed
- 20 still open
- Pull requests
- 145 merged
- 32 waiting
- Releases
- 4
- 1 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| robertknight / rten | 360 | yesterday | Apache-2.0 | No downloads |
| timtoole02 / Camelid | 220 | 24 days ago | MIT | Mac, Windows, Linux |
| FujitsuResearch / OneCompression | 445 | 7 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 89%
- Jupyter Notebook 11%
- PureBasic <1%
Topics
- deep-learning
- fpga
- inference
- machine-learning
- onnx
- quantization
- quantized-neural-networks
Project record
- JobLocal LLMs
- StatusListed
- Commits967
- Forks63
- Watching24
- Stars in 28 days+1
- CreatedJul 7, 2021
- First seen by usNov 7, 2026
- CheckedNov 8, 2026