Feature/tirex integration

.github/workflows/merge.yml

@@ -96,7 +96,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        example-name: [00-quickstart.ipynb, 01-multi-time-series-and-covariates.ipynb, 02-data-processing.ipynb, 03-FFT-examples.ipynb, 04-RNN-examples.ipynb, 05-TCN-examples.ipynb, 06-Transformer-examples.ipynb, 07-NBEATS-examples.ipynb, 08-DeepAR-examples.ipynb, 09-DeepTCN-examples.ipynb, 10-Kalman-filter-examples.ipynb, 11-GP-filter-examples.ipynb, 12-Dynamic-Time-Warping-example.ipynb, 13-TFT-examples.ipynb, 15-static-covariates.ipynb, 16-hierarchical-reconciliation.ipynb, 18-TiDE-examples.ipynb, 19-EnsembleModel-examples.ipynb, 20-SKLearnModel-examples.ipynb, 21-TSMixer-examples.ipynb, 22-anomaly-detection-examples.ipynb, 23-Conformal-Prediction-examples.ipynb, 24-SKLearnClassifierModel-examples.ipynb, 25-Chronos-2-examples.ipynb, 26-NeuralForecast-examples.ipynb, 27-Torch-and-Foundation-Model-Fine-Tuning-examples.ipynb]
+        example-name: [00-quickstart.ipynb, 01-multi-time-series-and-covariates.ipynb, 02-data-processing.ipynb, 03-FFT-examples.ipynb, 04-RNN-examples.ipynb, 05-TCN-examples.ipynb, 06-Transformer-examples.ipynb, 07-NBEATS-examples.ipynb, 08-DeepAR-examples.ipynb, 09-DeepTCN-examples.ipynb, 10-Kalman-filter-examples.ipynb, 11-GP-filter-examples.ipynb, 12-Dynamic-Time-Warping-example.ipynb, 13-TFT-examples.ipynb, 15-static-covariates.ipynb, 16-hierarchical-reconciliation.ipynb, 18-TiDE-examples.ipynb, 19-EnsembleModel-examples.ipynb, 20-SKLearnModel-examples.ipynb, 21-TSMixer-examples.ipynb, 22-anomaly-detection-examples.ipynb, 23-Conformal-Prediction-examples.ipynb, 24-SKLearnClassifierModel-examples.ipynb, 25-Chronos-2-examples.ipynb, 26-NeuralForecast-examples.ipynb, 27-Torch-and-Foundation-Model-Fine-Tuning-examples.ipynb, 28-TiRex-examples.ipynb]
     steps:
       - name: "Clone repository"
         uses: actions/checkout@v4

CHANGELOG.md

@@ -8,6 +8,8 @@ but cannot always guarantee backwards compatibility. Changes that may **break co
 [Full Changelog](https://github.com/unit8co/darts/compare/0.43.0...master)
 
 ### For users of the library:
+- 🚀🚀 Added new forecasting model `TiRexModel`: NX-AI's 35M-parameter pre-trained foundational model for zero-shot forecasting. It supports univariate, multivariate, and multiple time series forecasting without training and can output deterministic or probabilistic forecasts. [#3038](https://github.com/unit8co/darts/pull/3038) by [Lukas Fischer](https://github.com/lukfischer) and [Zhihao Dai](https://github.com/daidahao).
+  - Check out the new [TiRex Foundation Model Notebook](https://unit8co.github.io/darts/examples/28-TiRex-examples.html) for examples and usage of TiRex.
 
 - Added native multi-quantile support for `CatBoostModel` by using CatBoost’s `MultiQuantile` loss for faster training and inference. Set `likelihood="multiquantile"` to enable this feature. [#3032](https://github.com/unit8co/darts/pull/3032) by [Zhihao Dai](https://github.com/daidahao)
 

README.md

@@ -277,6 +277,7 @@ Here's a breakdown of the forecasting models currently implemented in Darts. Our
 | **Foundation Models**<br/>([GlobalForecastingModel](https://unit8co.github.io/darts/userguide/covariates.html#global-forecasting-models-gfms)): No training required                                                                                                                             |                                                                                                                                                                                                                                   |                                                              |                                                                          |                                                                          |                                           |
 | [Chronos2Model](https://unit8co.github.io/darts/generated_api/darts.models.forecasting.chronos2_model.html#darts.models.forecasting.chronos2_model.Chronos2Model)                                                                                                                                | [Chronos-2 report](https://arxiv.org/abs/2510.15821), [Amazon blog post](https://www.amazon.science/blog/introducing-chronos-2-from-univariate-to-universal-forecasting)                                                          | ✅ ✅                                                          | ✅ ✅ 🔴                                                                   | ✅ ✅                                                                      | ✅                                         |
 | [TimesFM2p5Model](https://unit8co.github.io/darts/generated_api/darts.models.forecasting.timesfm2p5_model.html#darts.models.forecasting.timesfm2p5_model.TimesFM2p5Model)                                                                                                                        | [TimesFM 1.0 paper](https://arxiv.org/abs/2310.10688), [Google blog post](https://research.google/blog/a-decoder-only-foundation-model-for-time-series-forecasting)                                                               | ✅ ✅                                                          | 🔴 🔴 🔴                                                                 | ✅ ✅                                                                      | ✅                                         |
+| [TiRexModel](https://unit8co.github.io/darts/generated_api/darts.models.forecasting.tirex_model.html#darts.models.forecasting.tirex_model.TiRexModel)                                                                                                           | [TiRex paper](https://arxiv.org/abs/2505.23719), [TiRex Github](https://github.com/NX-AI/tirex)                                                          | ✅ ✅                                                          | 🔴 🔴 🔴                                                                   | ✅ ✅                                                                      | ✅                                         |
 | **Ensemble Models**<br/>([GlobalForecastingModel](https://unit8co.github.io/darts/userguide/covariates.html#global-forecasting-models-gfms)): Model support is dependent on ensembled forecasting models and the ensemble model itself                                                           |                                                                                                                                                                                                                                   |                                                              |                                                                          |                                                                          |                                           |
 | [NaiveEnsembleModel](https://unit8co.github.io/darts/generated_api/darts.models.forecasting.baselines.html#darts.models.forecasting.baselines.NaiveEnsembleModel)                                                                                                                                |                                                                                                                                                                                                                                   | ✅ ✅                                                          | ✅ ✅ ✅                                                                    | ✅ ✅                                                                      | ✅                                         |
 | [RegressionEnsembleModel](https://unit8co.github.io/darts/generated_api/darts.models.forecasting.regression_ensemble_model.html#darts.models.forecasting.regression_ensemble_model.RegressionEnsembleModel)                                                                                      |                                                                                                                                                                                                                                   | ✅ ✅                                                          | ✅ ✅ ✅                                                                    | ✅ ✅                                                                      | ✅                                         |

darts/models/__init__.py

@@ -5,7 +5,7 @@
 A comprehensive collection of forecasting and filtering models, including baseline models
 (NaiveSeasonal, NaiveMovingAverage, ...), statistical models (ARIMA, exponential smoothing, ...),
 machine learning models (LightGBM, CatBoost, sklearn-based, ...), neural network models (RNN,
-N-BEATS, TiDE...), and foundation models (Chronos-2, TimesFM 2.5).
+N-BEATS, TiDE...), and foundation models (Chronos-2, TimesFM 2.5, TiRex).
 """
 
 from darts.logging import get_logger
@@ -89,11 +89,19 @@
 
 try:
     from darts.models.forecasting.chronos2_model import Chronos2Model
-    from darts.models.forecasting.timesfm2p5_model import TimesFM2p5Model
 except ModuleNotFoundError:
     Chronos2Model = NotImportedModule(module_name="(Py)Torch", warn=False)
+
+try:
+    from darts.models.forecasting.timesfm2p5_model import TimesFM2p5Model
+except ModuleNotFoundError:
     TimesFM2p5Model = NotImportedModule(module_name="(Py)Torch", warn=False)
 
+try:
+    from darts.models.forecasting.tirex_model import TiRexModel
+except ModuleNotFoundError:
+    TiRexModel = NotImportedModule(module_name="(Py)Torch", warn=False)
+
 try:
     from darts.models.forecasting.nf_model import NeuralForecastModel
 except ModuleNotFoundError:
@@ -211,5 +219,6 @@
     "ConformalQRModel",
     "Chronos2Model",
     "TimesFM2p5Model",
+    "TiRexModel",
     "NeuralForecastModel",
 ]

darts/models/forecasting/__init__.py

@@ -55,6 +55,7 @@
 Foundation Models (`GlobalForecastingModel <https://unit8co.github.io/darts/userguide/covariates.html#global-forecasting-models-gfms>`__)
     - :class:`~darts.models.forecasting.chronos2_model.Chronos2Model`
     - :class:`~darts.models.forecasting.timesfm2p5_model.TimesFM2p5Model`
+    - :class:`~darts.models.forecasting.tirex_model.TiRexModel`
 Ensemble Models (`GlobalForecastingModel <https://unit8co.github.io/darts/userguide/covariates.html#global-forecasting-models-gfms>`__)
     - :class:`~darts.models.forecasting.baselines.NaiveEnsembleModel`
     - :class:`~darts.models.forecasting.regression_ensemble_model.RegressionEnsembleModel`

darts/models/forecasting/foundation_model.py

@@ -165,7 +165,7 @@ def encode_year(idx):
             Default: ``None``.
         """
         # Set default fine-tuning to False for foundation models
-        if "enable_finetuning" not in self.model_params:
+        if self.model_params.get("enable_finetuning", None) is None:
             self.model_params["enable_finetuning"] = False
 
         # initialize `TorchForecastingModel` base class