v0.22.0

labring/FastGPTv0.22.0Jul 17, 2026by VikParuchuri

AI Summary

This release introduces a new model server architecture where models are spawned and shared across processes, replacing the previous per-process model model, and fixes a bug with text detection weights.

Key Highlights

Switched to a spawn + server model architecture
Fixed text detection weight loading bug
Models are now shared across multiple processes

New Features

New spawn + server model architecture

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