kendryte / nncase
Open deep learning compiler stack for Kendryte AI accelerators ✨
Why this job: works in the areas we cover, but does not say which job it does
What it does
- Supports multiple inputs and outputs and multi-branch structure
- Static memory allocation, no heap memory acquired
- Operators fusion and optimizations
- Support float and quantized uint8 inference
- Support post quantization from float model with calibration dataset
Get started
pip install nncase nncase-kpu- Maintenance
- Inactive
- Last commit 8 months ago
- Stars
- 901
- +1 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- 2 systems
- Mac, Linux
- Latest version
- v2.11.0
- Released 8 months ago
- Built with
- C#
- 56% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 99% closed
- 3 still open
- Pull requests
- 949 merged
- 8 waiting
- Releases
- 48
- 1 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| sophgo / tpu-mlir | 1,020 | 10 days ago | Custom | No downloads |
More: download files, languages, topics and project record
Download files, v2.11.0
- Mac5 files, 2,234 downloads
- Linux8 files, 4,456 downloads
Languages
- C# 56%
- C++ 32%
- Python 9%
- CMake 1%
Topics
- neural-network
- deep-learning
- kendryte
- k210
- k510
- k230
- ai-compiler
- llm
- compiler
Project record
- JobOther AI tools
- StatusListed
- Commits2,266
- Forks211
- Watching26
- Stars in 28 days+4
- CreatedApr 4, 2018
- First seen by usNov 7, 2026
- CheckedNov 8, 2026