AI Tools, Libraries, and Framework Optimizations
Develop, train, and deploy your AI solutions quickly with performance- and productivity-optimized tools from Intel.
Intel provides a comprehensive portfolio of tools for all your AI needs, including data preparation, training, inference, deployment, and scaling. All tools are built on the foundation of a standards-based, unified oneAPI programming model with interoperability, openness, and extensibility as core tenets.
Accelerate Data Analytics with Intel® Distribution of Modin*
Change one line of code to perform distributed pandas DataFrame processing. The library includes:
- Use of all available processing cores on your machine for DataFrame processing
- A choice of back-end distributed processing engines: built-in heterogeneous data kernels (HDK), Dask, Ray, or HEAVY.AI*
- API compatibility with pandas. So, just change import pandas as pd to import modin.pandas as pd
- Same notebook for running on your local machine and the cloud
Automate Model Compression with Intel® Neural Compressor
Reduce model size and speed up inference for deployment on CPUs or GPUs. The open source library includes:
- Automation to help you get started using quantization techniques
- A variety of pruning approaches
- Knowledge distillation from a larger model to improve the accuracy of a smaller model
- Support for models created with PyTorch*, TensorFlow*, Open Neural Network Exchange (ONNX*) Runtime, and Apache MXNet*
End-to-End Python* Data Science and AI Acceleration with Intel® AI Analytics Toolkit (AI Kit)
Accelerate end-to-end machine-learning and data-science pipelines, powered by oneAPI. The toolkit includes:
- Optimized frameworks, a model repository, and a low-precision optimization tool for deep learning
- Extensions for scikit-learn* and XGBoost for machine learning
- Accelerated data analytics through the Intel® Distribution of Modin* system
- Optimized core Python* libraries
- Samples for end-to-end workloads
Write Once, Deploy Anywhere with the Intel® Distribution of OpenVINO™ Toolkit
Deploy high-performance inference applications from device to cloud, powered by oneAPI. Optimize, tune, and run comprehensive AI inference using the included optimizer, runtime, and development tools. The toolkit includes:
- Repository of open source, pretrained, and preoptimized models ready for inference
- Model optimizer for your trained model
- Inference engine to run inference and output results on multiple processors, accelerators, and environments with a write-once, deploy-anywhere efficiency