anemoi-inference

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.

https://github.com/ecmwf/anemoi-inference