Auto-PyTorch vs AutoGluon
Auto-PyTorch
automl.github.io
AutoGluon
auto.gluon.aiSide by side
| Figure | Auto-PyTorch | AutoGluon |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 1 | 1 |
| Spec score · AutoML Software | 8.4 (#5) | 8.3 (#6) |
| Deployment | The project provides a Docker image and can be installed from PyPI or manually in a Python environment. | The project points to AutoGluon Cloud and deep learning containers for cloud training and deployment, and describes SageMaker Autopilot as a managed AutoGluon experience. |
| Integrations | The documentation describes using Dask.distributed for parallel Bayesian optimization and sklearn column transformers for data preprocessing. | AutoMM adapts models from Hugging Face, TIMM, and MMDetection model zoos. |
| License | The documentation states that Auto-PyTorch is licensed under the 3-clause BSD license. | The AutoGluon library is licensed under Apache 2.0. |
| Purpose | Auto-PyTorch is an automated machine learning toolkit based on PyTorch that automates algorithm selection and hyperparameter tuning. | AutoGluon automates machine learning for data such as tables and time series, helping users build predictive models with a few lines of code. |
| Supported tasks | The toolkit supports tabular classification, tabular regression, and time series forecasting. | The documentation includes image and text prediction, object detection, image segmentation, document prediction, entity extraction, and semantic matching examples. |
Plans
In their own words
Auto-PyTorch
Auto-PyTorch is a free, self-hosted machine-learning toolkit based on PyTorch. It automates algorithm selection and hyperparameter tuning, including neural-network architecture and training settings, within a user-defined search budget. Documented search methods include Bayesian optimisation, meta-learning, SMAC and Hyperband. Supported work includes tabular classification, tabular regression and time-series forecasting. Tabular preprocessing can perform imputation, categorical encoding, scaling and feature processing, while related hyperparameters are tuned. The toolkit can build ensembles from validation-set predictions, with controls for ensemble size and candidate limits. Users can set estimator memory limits and total wall time. Parallel Bayesian optimisation uses Dask.distributed; workers need shared filesystem access to training data and models. Installation documentation specifies Linux, Python 3.7 or later, a C++11-capable compiler and SWIG 3.0. SWIG 4.0 or later is unsupported. Forecasting needs extra dependencies. A Docker image and PyPI installation are documented, under the 3-clause BSD license.
AutoGluon
AutoGluon is a free, open-source Python library for automating machine learning across tabular, time-series, and multimodal data. For tables, it trains classification and regression models while handling data cleaning, feature engineering, hyperparameter optimization, and model selection. Its TimeSeriesPredictor produces probabilistic forecasts for multiple time series using historical data and related covariates. AutoMM reduces manual work in adapting foundation models to specialized data. Documentation examples cover image and text prediction, object detection, image segmentation, document prediction, entity extraction, and semantic matching. AutoMM can adapt models from Hugging Face, TIMM, and MMDetection collections. Forecasting methods include ETS and ARIMA from StatsForecast, LightGBM, DeepAR and Temporal Fusion Transformer from GluonTS, and Chronos. AutoGluon supports Python 3.10 through 3.13 on Linux, macOS, and Windows. GPU usage is not supported on macOS; the installation guide points GPU users to Linux or Windows. AutoGluon is licensed under Apache 2.0. Cloud options include AutoGluon Cloud, described as a free wrapper, and Amazon SageMaker, where compute and S3 storage are billed to the user’s AWS account.