Metadata-Version: 2.5
Name: multihull
Version: 0.0.1
Summary: Deploy always-warm GPU inference containers to many providers from one spec and fail over between them automatically.
Project-URL: Homepage, https://multihull.pages.dev
Project-URL: Documentation, https://multihull.pages.dev
Project-URL: Repository, https://github.com/mishraprafful/multihull
Author: Prafful Mishra
License-Expression: Apache-2.0
Keywords: failover,gpu,inference,kubernetes,modal,runpod,serving
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: System :: Distributed Computing
Requires-Python: >=3.11
Description-Content-Type: text/markdown

# multihull

Deploy always-warm GPU inference containers to many providers from one YAML spec, serve them behind one URL, and fail over between providers automatically. Built for robustness and reliability over cost.

This release reserves the package name while the project is in its design phase. Documentation: https://multihull.pages.dev
