LightGBM

PyTorch

pytorch/pytorch

Popular

Dominant deep learning framework for research and production; the foundation of nearly all modern LLM work.

scikit-learn

scikit-learn/scikit-learn

Popular

Standard Python library for classical ML: classification, regression, clustering, pipelines and metrics.

JAX

jax-ml/jax

Composable transformations (grad, jit, vmap) of NumPy programs on GPU/TPU; powers Google DeepMind research.

Keras

keras-team/keras

High-level deep learning API that runs on JAX, PyTorch or TensorFlow backends since Keras 3.

TensorFlow

tensorflow/tensorflow

Legacy

Google's original deep learning framework, still in many production systems but losing ground to PyTorch and JAX.

XGBoost

dmlc/xgboost

Popular

Optimized gradient boosting library and the go-to choice for tabular data and Kaggle-style problems.

CatBoost

catboost/catboost

Gradient boosting library from Yandex with native categorical feature handling and strong defaults.

PyTorch Lightning

Lightning-AI/pytorch-lightning

Organizes PyTorch code and handles multi-GPU, mixed precision and checkpointing boilerplate.

ONNX

onnx/onnx

Open interchange format for ML models, used to move models between frameworks and inference runtimes.