Open Source High-Performance ML Libraries
BrainCog (Brain-inspired Cognitive Intelligence Engine) is a brain-inspired spiking neural network based platform for Brain-inspired Artificial Intelligence and simulating brains at multiple scales.
License: Apache License 2.0
Composer is a PyTorch library that enables you to train neural networks faster, at lower cost, and to higher accuracy.
License: Apache License 2.0
Built based on the Apache Arrow columnar memory format, cuDF is a GPU DataFrame library for loading, joining, aggregating, filtering, and otherwise manipulating data.
License: Apache License 2.0
cuML is a suite of libraries that implement machine learning algorithms and mathematical primitives functions that share compatible APIs with other RAPIDS projects.
License: Apache License 2.0
An implementation of NumPy-compatible multi-dimensional array on CUDA. CuPy consists of the core multi-dimensional array class, cupy.ndarray, and many functions on it.
License: MIT License
A neural network library and ecosystem for JAX designed for flexibility.
License: Apache License 2.0
Fast scalable Machine Learning platform for smarter applications: Deep Learning, Gradient Boosting & XGBoost, Random Forest, Generalized Linear Modeling (Logistic Regression, Elastic Net), K-Means, PCA, Stacked Ensembles, Automatic Machine Learning (AutoML), etc..
License: Apache License 2.0
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more.
License: Apache License 2.0
Speed up your Pandas workflows by changing a single line of code.
License: Apache License 2.0
Nebullvm is an ecosystem of plug and play modules to boost the performances of your AI systems. The optimization modules are stack-agnostic and work with any library. They are designed to be easily integrated into your system, providing a quick and seamless boost to its performance.
License: Apache License 2.0
Nevergrad is a gradient-free optimization platform.
License: MIT License
Norse aims to exploit the advantages of bio-inspired neural components, which are sparse and event-driven - a fundamental difference from artificial neural networks.
License: GNU Lesser General Public License v3.0
A compiler for Python array and numerical functions.
License: BSD 2-Clause "Simplified" License
OpenFlamingo is an open-source framework for training large multimodal models.
License: MIT License
OpenVINO is an open-source toolkit for optimizing and deploying AI inference.
License: Apache License 2.0
Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of pre-trained language models (PLMs) to various downstream applications without fine-tuning all the model’s parameters.
License: Apache License 2.0
snnTorch is a deep and online learning library with spiking neural networks in Python
License: MIT License
Tensor2Tensor is a library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
License: Apache License 2.0
TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
License: Apache License 2.0
Blazing fast, lightweight and mobile phone-enabled Vulkan compute framework optimized for advanced GPU data processing usecases.
License: Unknown
High-performance runtime for data analytics applications, Here is an interview with Weld’s main contributor.
License: BSD 3-Clause "New" or "Revised" License
XGBoost is an optimized distributed gradient boosting library designed to be highly efficient, flexible and portable.
License: Apache License 2.0
Last Updated: Dec 26, 2023