LightGBM is a gradient boosting framework that uses tree based learning algorithms. It is designed to be distributed and efficient with the following advantages:

• Faster training speed and higher efficiency

• Lower memory usage

• Better accuracy

• Parallel and GPU learning supported (not enabled in this package)

• Capable of handling large-scale data

NNPACK is an acceleration package for neural network computations. NNPACK aims to provide high-performance implementations of convnet layers for multi-core CPUs.

NNPACK is not intended to be directly used by machine learning researchers; instead it provides low-level performance primitives leveraged in leading deep learning frameworks, such as PyTorch, Caffe2, MXNet, tiny-dnn, Caffe, Torch, and Darknet.

ONNX Interface for Framework Integration is a cross-platform API for loading and executing ONNX graphs on optimized backends. This package contains facebook extensions and is used by PyTorch.

This is a package for hassle-free computation of shareable, comparable, and reproducible BLEU, chrF, and TER scores for natural language processing.

OneAPI Deep Neural Network Library (oneDNN) is a cross-platform performance library of basic building blocks for deep learning applications.

GPy is a Gaussian Process (GP) framework written in Python, from the Sheffield machine learning group. GPy implements a range of machine learning algorithms based on GPs.

CTranslate2 is a C++ and Python library for efficient inference with Transformer models.

The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU.

BoTorch is a library for Bayesian Optimization built on PyTorch.

Dlib is a modern C++ toolkit containing machine learning algorithms and tools. It is used in both industry and academia in a wide range of domains including robotics, embedded devices, mobile phones, and large high performance computing environments.

This package provides an implementation of today’s most used tokenizers, with a focus on performance and versatility.

This is a Python library that aims at making tensor learning simple and accessible. It allows performing tensor decomposition, tensor learning and tensor algebra easily. Its backend system allows seamlessly perform computation with NumPy, PyTorch, JAX, MXNet, TensorFlow or CuPy and run methodxs at scale on CPU or GPU.

cleanlab automatically finds and fixes errors in any ML dataset. This data-centric AI package facilitates machine learning with messy, real-world data by providing clean labels during training.

A Python library for reading and writing GGUF & GGML format ML models.

Captum is a model interpretability and understanding library for PyTorch. Captum contains general purpose implementations of integrated gradients, saliency maps, smoothgrad, vargrad and others for PyTorch models. It has quick integration for models built with domain-specific libraries such as torchvision, torchtext, and others.

LIBSVM is a machine learning library for support vector classification, (C-SVC, nu-SVC), regression (epsilon-SVR, nu-SVR) and distribution estimation (one-class SVM). It supports multi-class classification.

Autograd can automatically differentiate native Python and NumPy code. It can handle a large subset of Python's features, including loops, ifs, recursion and closures, and it can even take derivatives of derivatives of derivatives. It supports reverse-mode differentiation (a.k.a. backpropagation), which means it can efficiently take gradients of scalar-valued functions with respect to array-valued arguments, as well as forward-mode differentiation, and the two can be composed arbitrarily. The main intended application of Autograd is gradient-based optimization.

This package is a stand-alone implementation of several NumPy dtype extensions used in machine learning libraries, including:

• bfloat16: an alternative to the standard float16 format

• float8_*: several experimental 8-bit floating point representations including:

  • float8_e4m3b11fnuz

  • float8_e4m3fn

  • float8_e4m3fnuz

  • float8_e5m2

  • float8_e5m2fnuz

• int4 and uint4: low precision integer types.

FANN is a neural network library, which implements multilayer artificial neural networks in C with support for both fully connected and sparsely connected networks.

TensorFlow is a flexible platform for building and training machine learning models. This package provides the "lite" variant for mobile devices.

DMLC-Core is the backbone library to support all DMLC projects, offers the bricks to build efficient and scalable distributed machine learning libraries.

This Python library provides several solvers for optimization problems related to Optimal Transport for signal, image processing and machine learning.

Inquirer should ease the process of asking end user questions, parsing, validating answers, managing hierarchical prompts and providing error feedback.

GPyTorch is a Gaussian process library implemented using PyTorch.

fastText is a library for efficient learning of word representations and sentence classification.