huawei-noah/bolt
Bolt is a deep learning library with high performance and heterogeneous flexibility.
This is a lightweight tool for deep learning developers who need to get their trained neural networks running quickly and efficiently on a wide variety of hardware. It takes models trained in frameworks like Caffe, ONNX, TFLite, and Tensorflow, then optimizes and compiles them into a highly performant inference engine. Data scientists and machine learning engineers can use this to deploy their models to edge devices or servers with minimal overhead.
957 stars. No commits in the last 6 months.
Use this if you need to deploy your trained neural network models to different hardware platforms and demand the highest possible inference speed and minimal memory footprint.
Not ideal if you are still in the model development and training phase, as Bolt focuses on model deployment and acceleration rather than model creation.
Stars
957
Forks
164
Language
C++
License
MIT
Category
Last pushed
Apr 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/huawei-noah/bolt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
mlverse/torch
R Interface to Torch
modern-fortran/neural-fortran
A parallel framework for deep learning
Beliavsky/Fortran-code-on-GitHub
Directory of Fortran codes on GitHub, arranged by topic
Cambridge-ICCS/FTorch
A library for directly calling PyTorch ML models from Fortran.
NVIDIA/TorchFort
An Online Deep Learning Interface for HPC programs on NVIDIA GPUs