Neural Magic 1.2 Product Release (Version Number Deprecated)


NOTE: As of February 2021, our products have been renamed and versions re-numbered; most have been open-sourced and their release notes can be found in GitHub!

We are excited to announce the Neural Magic 1.2 product release. This product milestone contains new feature updates, an improved user experience, and stability enhancements that will simplify the ability for our clients to achieve price performance on commodity CPUs. 

Neural Magic Inference Engine

Enables clients to run mission critical deep learning models on commodity CPUs to reduce cost per inferences and generate price-performant deployments. This feature set includes the inference engine, ONNX conversion tooling, model server if needed, and is focused on model deployment and scaling machine learning pipelines.
  • Support for Ubuntu 20.04 
  • Licensing for user activation and software management 
  • Added operators for performance - ReduceMin, ReduceMax, ReduceMean, Pow, Sqrt
  • Preliminary quantized convolutions and operators for performance

Neural Magic ML Tooling

Enables data scientists to optimize their model for performance without having to sacrifice accuracy required for business outcomes. This feature set includes model pruning APIs and CLIs as well as transfer learning APIs and CLIs, simplifying the process of achieving performance on deep learning models with Neural Magic. 

  • Support for PyTorch 1.6
  • PyTorch SSD API usability improvements via training and pruning examples
  • TensorFlow SSD API usability improvements via training and pruning examples
  • Post-Training Quantization support for ONNX, enabling quantized graph outputs to run in the Neural Magic Inference Engine

Neural Magic Model Repo

Simplify time to value and reduce skill burden to build performant deep learning models by having a collection of pre-trained, performance-optimized deep learning models to prototype from. The repository consists of popular image classification and object detection models and is constantly growing. 

Performant model additions:
  • ResNet-18
  • ResNet-34
  • ResNet-50-SSD-300

For more details, check our in-depth release notes. Or if you are interested in trying our software, visit our GitHub repos.

Gaurav Rao
Head of Product