Metadata-Version: 2.1
Name: remote-graphcast
Version: 0.0.3
Summary: Allows people without massive GPUs to easily run graphcast on remote runpod servers
Home-page: https://github.com/Lewington-pitsos/remote-graphcast
Author: Louka Ewington-Pitsos
Author-email: lewingtonpitsos@gmail.com
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: boto3
Requires-Dist: ai_models_graphcast
Requires-Dist: climetlab
Requires-Dist: runpod

# Remote Graphcast

Run graphcast on a runpod GPU. Output is saved to s3.

## Order of operations

1. Input is validated
2. A secure runpod GPU pod is spun up on your account
3. Graphcast is installed into that gpu and forcasts of your chosen length are generated for each timestamp, this takes around 10 minutes for a 10 day forcast
4. These forcasts are saved to your chosen s3 bucket, roughly 6.5GB for 10 days of forcast
5. The runpod pod is terminated
6. The program exits

## Requirements

- python 3.10+ and pip
- cds.climate credentials
- an s3 bucket
- S3 credentials to go with the bucket
- Runpod credentials

## Installation

## Notes

