#153153rd of 206 in ML frameworks and librariesFor data and documents, data analysis
gluonts
Python library for probabilistic time series forecasting with PyTorch models
- Stars
- 5.3k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Jul 2026
- Language
- Python
5,144 on 21 Apr 20265,260 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
GluonTS is a Python package for training and evaluating probabilistic time series models, focused on deep learning and built on PyTorch. The README example trains a DeepAR estimator on the AirPassengers dataset and plots forecasts with 50% and 90% prediction intervals. It includes a pandas dataset wrapper and train/test splitting utilities.
Who it is for: Data scientists and ML engineers building forecasting models in Python
Strengths
- Forecasts are probability distributions with prediction intervals, not only point estimates
- Provides PandasDataset and a split utility for backtest windows
- Installs from PyPI with a torch extra; supports Python 3.10 to 3.14
- Stable and dev docs plus several conference tutorials with videos
Weaknesses
- Library only: requires writing Python, no UI or server component
- README shows only DeepAR; the full model list is in the docs
- Pretrained zero-shot forecasting lives in a separate project, Chronos
- Torch models need the optional gluonts[torch] extra
What it needs
- Needs PyTorch, pandas, matplotlib
- Models: DeepAR, PyTorch
What changed
- v0.17.0 ↗ (opens in a new tab)Security fix
“[Security] Resolve security issue for torch.load by @jalencato in https://github.com/awslabs/gluonts/pull/3304”
- v0.16.3 ↗ (opens in a new tab)Security fix
“[Security] Resolve security issue for torch.load #3304”
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in ML frameworks and libraries
See all 206| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | ultralyticsPython library and CLI for training and running YOLO vision models | 94 out of 100 |
| 3 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |