Rex Framework Package Docs¶
Rex Framework is a package for inference with remotely stored model weights. It fetches chunks on demand, keeps residency bounded, and lets the full model stay remote.
This site documents the installed package only. It does not cover private repository internals, ADRs, or development workflow.
What the package gives you¶
- Python APIs for loading manifests and running inference.
- CLI tools for conversion, validation, inspection, serving, benchmarking, and demo runs.
- Notebook-friendly usage patterns for Kaggle and Google Colab.
- WebSocket streaming as an explicit backend mode for live weight delivery from
rex-serve. - Configuration via
RexConfigandREX_*environment variables. - Manifest hints such as
storage_backend: streaming_wsandprovenance.base_urlfor hosted chunks.
Start here¶
- Read the install guide.
- Follow the Kaggle notebook guide or Colab guide if you are running in a notebook.
- Review streaming if you want live weight delivery through
rex-serve. - Use configuration for runtime tuning.
Common package story¶
pip install "rex-framework[pytorch]"
rex-serve --dir ./rex_output/weights --port 8080
Then point your runtime at the manifest and base URL for the chunk host.