amazon-science/chronos-forecasting v2.3.0

2.3.0

Repository: amazon-science/chronos-forecasting

Tag: v2.3.0

Published: 2026-06-18T11:30:31Z

Prerelease: no

Release notes:

What's Changed

🚀 Highlights

• New cloud deployment guide: run Chronos-2 on AWS in 3 lines of code
• Fine-tuning with Chronos2Pipeline.fit() now supports larger-than-memory datasets
• New efficient preprocessing module chronos.chronos2.preprocess resulting in up to 20x faster input preprocessing for Chronos-2
• Support for transformers>=5 and pandas>=3

❗Deprecations & breaking changes

• When providing inputs to Chronos2Pipeline as a list[dict], all dictionaries must share the same schema (same number of target dimensions and same covariate keys). To forecast inputs with different schemas, loop over them and call the model once per schema.

# ❌ Different covariate keys across items — no longer allowed
pipeline.predict([
{"target": [...], "past_covariates": {"price": [...], "promo": [...]}},
{"target": [...], "past_covariates": {"price": [...]}},
])

# ❌ Mixed univariate and multivariate targets — no longer allowed
pipeline.predict([
{"target": np.zeros(100)}, # shape (history_length,)
{"target": np.zeros((3, 100))}, # shape (n_variates, history_length)
])

• Following methods have been deprecated. Please use chronos.chronos2.preprocess.from_* and helpers from chronos.df_utils instead.
• Input preparation methods in chronos.chronos2.dataset:.
• Chronos2Dataset.convert_inputs
• validate_and_prepare_single_dict_task
• convert_list_of_tensors_input_to_list_of_dicts_input
• convert_tensor_input_to_list_of_dicts_input
• convert_fev_window_to_list_of_dicts_input
• DataFrame utilities in chronos.df_utils:
• convert_df_input_to_list_of_dicts_input
• validate_df_inputs
• Removed dependency on scikit-learn

✨ New features

• Add support for transformers>=5.0 by @kashif in https://github.com/amazon-science/chronos-forecasting/pull/416
• New module chronos.chronos2.preprocess with efficient preprocessing methods for Chronos-2 by @shchur in https://github.com/amazon-science/chronos-forecasting/pull/466, https://github.com/amazon-science/chronos-forecasting/pull/493, https://github.com/amazon-science/chronos-forecasting/pull/506
• Public API of Chronos2Pipeline now accepts preprocessed data (e.g. backed by a memory-mapped Hugging Face datasets.Dataset) by @shchur in https://github.com/amazon-science/chronos-forecasting/pull/507, https://github.com/amazon-science/chronos-forecasting/pull/512

🐛 Bugfixes & improvements

• Allow explicitly passing the frequency to pipeline.predict_df by @shchur in https://github.com/amazon-science/chronos-forecasting/pull/449
• Fix XDG_CACHE_HOME typo in boto_utils by @shaun0927 in https://github.com/amazon-science/chronos-forecasting/pull/488
• Defer boto3 import and raise actionable ImportError for s3:// loads by @shaun0927 in https://github.com/amazon-science/chronos-forecasting/pull/489
• Fix pip install command for chronos-forecasting by @Arseni1919 in https://github.com/amazon-science/chronos-forecasting/pull/481
• Minor fixes and improvements by @abdulfatir, @shchur in https://github.com/amazon-science/chronos-forecasting/pull/467, https://github.com/amazon-science/chronos-forecasting/pull/505, https://github.com/amazon-science/chronos-forecasting/pull/510, https://github.com/amazon-science/chronos-forecasting/pull/511,

📚 Documentation

• Describe deployment options via AutoGluon-Cloud by @shchur in https://github.com/amazon-science/chronos-forecasting/pull/503
• Update notebook on Chronos-2 deployment to SageMaker by @shchur in https://github.com/amazon-science/chronos-forecasting/pull/444

New Contributors

• @Arseni1919 made their first contribution in https://github.com/amazon-science/chronos-forecasting/pull/481
• @shaun0927 made their first contribution in https://github.com/amazon-science/chronos-forecasting/pull/488

Full Changelog: https://github.com/amazon-science/chronos-forecasting/compare/v2.2.2...v2.3.0