Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Bolt is a deep learning library with high performance and heterogeneous flexibility.
| Date | Stars |
|---|---|
| 2026-07-24 | 958 |
| 2026-07-25 | 957 |
| 2026-07-28 | 957 |
| 2026-07-30 | 957 |
| 2026-07-31 | 958 |
| 2026-08-06 | 959 |
Today
+1 stars today
This week
+2 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.21%/day
# Introduction --- [](https://opensource.org/licenses/MIT) [Bolt](https://huawei-noah.github.io/bolt/) is a light-weight library for deep learning. Bolt, as a universal deployment tool for all kinds of neural networks, aims to automate the deployment pipeline and achieve extreme acceleration. Bolt has been widely deployed and used in many departments of HUAWEI company, such as 2012 Laboratory, CBG and HUAWEI Product Lines. If you have questions or suggestions, you can submit issue. **QQ群: 833345709** # Why Bolt is what you need? --- - **High Performance:** **15%+** faster than existing open source acceleration libraries. - **Rich Model Conversion:** support Caffe, ONNX, TFLite, Tensorflow. - **Various Inference Precision:** support FP32, FP16, INT8, 1-BIT. - **Multiple platforms:** ARM CPU(v7, v8, v8.2+, v9), X86 CPU(AVX2, AVX512), GPU(Mali, Qualcomm, Intel, AMD) - **Bolt is the first to support NLP and also supports common CV applications.** - **Minimize ROM/RAM** - Rich Graph Optimization - Efficient Thread Affinity Setting - [Auto Algorithm Tuning](https://zhuanlan.zhihu.com/p/336218879) - [Time-Series Data Acceleration](docs/USER_HANDBOOK.md#time-series-data-acceleration) [See more excellent features and details here](https://zhuanlan.zhihu.com/p/317111024) # Building Status --- There are some common used platform for inference. More targets can be seen from [scripts/target.sh](scripts/target.sh). Please make a suitable choice depending on your environment. If you want to build on-device training module, you can add **--train** option. If you want to use multi-threads parallel, you can add **--openmp** option. If you want to build for cortex-M or cortex-A7 with restricted ROM/RAM(Sensor, MCU), you can see [docs/LITE.md](docs/LITE.md). *Bolt defaultly link static library, This may cause some problem on some platforms. You can use --shared option to link shared library.* | target platform | precision | build command | Linux | Windows | MacOS | | ---------------------- | ------------------ | ---------------------------------------------------- | ----- | ------- | ----- | | Android(armv7) | fp32,int8 | ./install.sh --target=android-armv7 | [](https://github.com/huawei-noah/bolt/actions?query=workflow%3Alinux-android-armv7) | [](https://github.com/huawei-noah/bolt/actions?query=workflow%3Awindows-android-armv7) | [](https://github.com/huawei-noah/bolt/actions?query=workflow%3Amacos-android-armv7) | | Android(armv8) | fp32,int8 | ./install.sh --target=android-aarch64 --fp16=off | [](https://github.com/huawei-noah/bolt/actions?query=workflow%3Alinux-android-armv8) | [](https://github.com/huawei-noah/bolt/actions?query=workflow%3Awindows-android-armv8) | [](https://github.com/huawei-noah/bolt/actions?query=workflow%3Amacos-android-armv8) | | Android(armv8.2+) | fp32,fp16,int8,bnn | ./install.sh --target=android-aarch64 | [](https://github.com/huawei-noah/bolt/actions?query=workflow%3Alinux-a
Excerpt of 20,262 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b20deba8a441a255, topic:inference, topic:onnx
matched fp:b20deba8a441a255, topic:deep-learning, topic:tensorflow
matched fp:b20deba8a441a255, topic:nlp
