v0.21.0

Tencent/WeKnorav0.21.0Jul 8, 2026by VikParuchuri

AI Summary

This release introduces a new fast layout model optimized for CPU execution, along with updates to the model path configuration.

Key Highlights

  • Added a new fast layout model
  • Model runs on CPU
  • Model path swap

New Features

  • Fast layout model for CPU

Full Release Notes

- Added a new fast layout model that can run on CPU

## What's Changed
* Vik/fast models by @VikParuchuri in https://github.com/datalab-to/surya/pull/524
* Swap model path by @VikParuchuri in https://github.com/datalab-to/surya/pull/525
* Dev by @VikParuchuri in https://github.com/datalab-to/surya/pull/526


**Full Changelog**: https://github.com/datalab-to/surya/compare/v0.20.0...v0.21.0