lightgbm-org/LightGBM

Project overview

Training gradient boosting models on large-scale data is typically slow and memory-intensive, but this framework directly addresses that bottleneck by offering faster training speed and higher efficiency with lower memory usage compared to existing boosting frameworks.

Project type: Model Development · Data Processing
Use cases: Data Analysis
Deployment: Refer to project documentation
License: MIT

Best for

Developers, data teams, and researchers who need to train gradient boosting models on large-scale data.

Key capabilities

A gradient boosting framework that uses tree based learning algorithms.
Support for distributed learning capable of handling large-scale data.
Support for GPU learning to speed up computation.

Limitations and risks

Users need coding knowledge to interact with the framework through its CLI or as a library.

Getting started

Setup is easy because the project is available on PyPI and conda-forge; users can get started with the command: pip install lightgbm.

Evidence and sources

GitHub project description: A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other…
README: 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…
README: [**Examples**](https://github.com/lightgbm-org/LightGBM/tree/main/examples) showing command line usage of common tasks.

Reviewed at: 2026-07-19T18:33:05Z