LightGBM and GBM-perf
One tool is a fast, distributed gradient boosting framework, while the other is a project for evaluating the performance of various open-source gradient boosting implementations; therefore, they are complements, as the latter can be used to benchmark and understand the former.
About LightGBM
lightgbm-org/LightGBM
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 machine learning tasks.
Implements leaf-wise tree growth with histogram-based learning to reduce memory footprint and accelerate training on CPU and GPU hardware. Provides native bindings for Python, R, and C++, with ecosystem integrations including FLAML for AutoML, Optuna for hyperparameter tuning, and model compilers like Treelite and Hummingbird for production deployment.
About GBM-perf
szilard/GBM-perf
Performance of various open source GBM implementations
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work