Add update for new SageMaker deployment guide
#3
by
shchuro
- opened
README.md
CHANGED
|
@@ -21,6 +21,9 @@ library_name: chronos-forecasting
|
|
| 21 |
---
|
| 22 |
|
| 23 |
# Chronos-2
|
|
|
|
|
|
|
|
|
|
| 24 |
**Chronos-2** is a 120M-parameter, encoder-only time series foundation model for zero-shot forecasting.
|
| 25 |
It supports **univariate**, **multivariate**, and **covariate-informed** tasks within a single architecture.
|
| 26 |
Inspired by the T5 encoder, Chronos-2 produces multi-step-ahead quantile forecasts and uses a group attention mechanism for efficient in-context learning across related series and covariates.
|
|
|
|
| 21 |
---
|
| 22 |
|
| 23 |
# Chronos-2
|
| 24 |
+
|
| 25 |
+
**Update Dec 30, 2025:** ☁️ Deploy Chronos-2 on Amazon SageMaker. [New guide](https://github.com/amazon-science/chronos-forecasting/blob/main/notebooks/deploy-chronos-to-amazon-sagemaker.ipynb) covers real-time GPU and CPU inference, serverless endpoints (run on demand, no idle costs), and batch transform for large-scale forecasting.
|
| 26 |
+
|
| 27 |
**Chronos-2** is a 120M-parameter, encoder-only time series foundation model for zero-shot forecasting.
|
| 28 |
It supports **univariate**, **multivariate**, and **covariate-informed** tasks within a single architecture.
|
| 29 |
Inspired by the T5 encoder, Chronos-2 produces multi-step-ahead quantile forecasts and uses a group attention mechanism for efficient in-context learning across related series and covariates.
|