MNN is a deep learning framework. It supports inference and training of deep learning models for inference and training on-device.

Stanza is a collection of accurate and efficient tools for the linguistic analysis of many human languages. Starting from raw text, Stanza divides it into sentences and words, and then can recognize parts of speech and entities, do syntactic analysis, and more.

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

BoTorch is a library for Bayesian Optimization built on PyTorch.

Gloo is a collective communications library. It comes with a number of collective algorithms useful for machine learning applications. These include a barrier, broadcast, and allreduce.

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

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.

Hmmlearn is a set of algorithms for unsupervised learning and inference of Hidden Markov Models.

This package provides a collection of ordinal regression models for machine learning in Python. They are intended to be used with scikit-learn and are compatible with its API.

This package provides a tensor-like library for functions and distributions.

LinearOperator is a PyTorch package for abstracting away the linear algebra routines needed for structured matrices (or operators).

ONNX is a format for AI models, both deep learning and traditional ML. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types.

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

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

This package provides fast machine learning algorithms including matrix factorization and divisive clustering for large sparse and dense matrices.

Scikit-learn provides simple and efficient tools for data mining and data analysis.

This package provides a generic API for dispatch to Pyro backends.

Kaldi is an extensible toolkit for speech recognition written in C++.

This is a real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framework and implemented in Python.

This package contains legacy registered functions for spaCy backwards compatibility.

PyTorch is a Python package that provides two high-level features:

• tensor computation (like NumPy) with strong GPU acceleration;

• deep neural networks (DNNs) built on a tape-based autograd system.

You can reuse Python packages such as NumPy, SciPy, and Cython to extend PyTorch when needed.

Note: currently this package does not provide GPU support.

ML Collections is a library of Python collections designed for Machine Learning usecases.

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.

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