huawei-noah/bolt
A Huawei deep learning library for high-performance neural network inference acceleration across heterogeneous hardware platforms.
Not currently ranked — collecting fresh signals.
star history
Bolt is a light-weight deep learning inference library developed by Huawei that aims to automate neural network deployment and achieve extreme acceleration. It supports model conversion from Caffe, ONNX, TFLite, and TensorFlow, and targets multiple platforms including ARM CPUs (v7, v8, v8.2+, v9), x86 CPUs (AVX2, AVX512), and GPUs from Mali, Qualcomm, Intel, and AMD. The library offers various inference precisions including FP32, FP16, INT8, and 1-bit quantization, and has been widely deployed across Huawei’s internal departments.
Frequently asked
- What is huawei-noah/bolt?
- A Huawei deep learning library for high-performance neural network inference acceleration across heterogeneous hardware platforms.
- Is bolt open source?
- Yes — huawei-noah/bolt is open source, released under the MIT license.
- What language is bolt written in?
- huawei-noah/bolt is primarily written in C++.
- How popular is bolt?
- huawei-noah/bolt has 958 stars on GitHub.
- Where can I find bolt?
- huawei-noah/bolt is on GitHub at https://github.com/huawei-noah/bolt.