v0.22.0

lm-sys/RouteLLMv0.22.0Jul 17, 2026by VikParuchuri

AI Summary

This release introduces a new 'spawn + server' model architecture to reduce memory overhead by avoiding loading models in every process, alongside a fix for text detection weight loading.

Key Highlights

  • Switched to a spawn + server model architecture
  • Fixed text detection weights loading bug

New Features

  • Server-based model architecture for efficiency

Full Release Notes

Swap models to a spawn + server model, instead of relying on each process having a separate model.
Fix bug with text detection where weights didn't load properly.

## What's Changed
* Vik/fast models by @VikParuchuri in https://github.com/datalab-to/surya/pull/532
* Dev by @VikParuchuri in https://github.com/datalab-to/surya/pull/533


**Full Changelog**: https://github.com/datalab-to/surya/compare/v0.21.2...v0.22.0