Neural Magic delivers best-in-class deep learning performance on commodity CPUs. We do this via:
- Model optimization techniques like pruning and quantization
- Smart algorithms that utilize CPU memory more effectively.
To help visualize the power of Neural Magic, we recorded three short end-to-end video guides on how to install our software, prepare and run a model for inference, and finally benchmark for performance.
Check them out below! And if you'd like to use our tools and techniques to speed up your models, please visit our GitHub repos.
TensorFlow End-to-End Demo
This is an end-to-end guide on how to install our software, prepare and run a TensorFlow model for inference, and finally benchmark for performance.
PyTorch End-to-End Demo
This is an end-to-end guide on how to install our software, prepare and run a PyTorch model for inference, and finally benchmark for performance.
Neural Magic Model Repo End-to-End Demo
This is an end-to-end guide on how to install our software, prepare and run a Neural Magic model for inference, and finally benchmark for performance.
What's Next?
If you'd like to use our tools and techniques to speed up your models, please visit our GitHub repos.