# anemoi-inference Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/anemoi-inference
> Markdown URL: https://aitinkerers.org/technologies/anemoi-inference.md
> Technology record last updated: 2026-03-30T15:00:00Z
> Generated: 2026-09-21T17:34:39Z

A high-performance inference engine for ECMWF’s Anemoi graph neural network framework, optimized for global weather forecasting.

Anemoi-inference provides the operational runtime for data-driven weather models built with the Anemoi framework. It handles the deployment of Graph Neural Networks (GNNs) by managing stateful rollouts and integrating seamlessly with ECMWF’s MARS archive and FDB fields database. The package supports ONNX and PyTorch backends to execute complex atmospheric simulations (like the AIFS) with sub-degree precision and significantly lower computational overhead than traditional numerical weather prediction systems.

- Official technology site: https://github.com/ecmwf/anemoi-inference
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [A playground to run AIFS experiments using serverless inference](https://zurich.aitinkerers.org/talks/rsvp_2Nwv7NahQs4)

The aifs-modal library is a thin serverless wrapper to easily run AIFS inference (for forecasts or reforecasts) on a rented GPU in one Python call, storing the outputs in a versioned Zarr store using Icechunk. The demo shows how (claude and) I wired together anemoi-inference (ECMWF's model runtime), Modal (serverless GPU), and Icechunk (git-like array storage) to get reproducible forecasts or reforecasts from any historical date, all driven from a local Jupyter notebook with no cluster, no Colab, no infrastructure to manage. Initial conditions can be ingested from ECMWF operational analysis or ERA5 reanalysis out of the box. Once the GPU job finishes, the output is managed in a versioned Icechunk store and opens instantly in your local notebook as an xarray Dataset for postprocessing. Ensemble forecasts are also supported: each member runs on a separate GPU in parallel, with members writing concurrently into the same Icechunk store.

- Event context: AI Tinkerers Zurich April 9th — 2026-04-09 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_2Nwv7NahQs4

## Related Technologies

- [AIFS](https://aitinkerers.org/technologies/aifs) ([Markdown](https://aitinkerers.org/technologies/aifs.md)) — 1 public demo
- [Icechunk](https://aitinkerers.org/technologies/icechunk) ([Markdown](https://aitinkerers.org/technologies/icechunk.md)) — 1 public demo
- [Modal](https://aitinkerers.org/technologies/modal) ([Markdown](https://aitinkerers.org/technologies/modal.md)) — 14 public demos
- [xarray](https://aitinkerers.org/technologies/xarray) ([Markdown](https://aitinkerers.org/technologies/xarray.md)) — 1 public demo