Starstruk Logo MarkStarstruk

v0.30.0

TabbyML/tabbyv0.30.0Jul 2, 2025by github-actions[bot]

AI Summary

A minor release introducing GitLab Merge Request context indexing and upgrading the default base image to CUDA 12, while noting a mandatory GPU requirement for Docker.

Key Highlights

  • Support for indexing GitLab Merge Requests as context.
  • Docker image now requires an NVIDIA GPU (CPU-only users must use Linux binary).
  • Answer Engine logic enrichment for improved page quality.

Breaking Changes

  • The Tabby Docker image now requires an NVIDIA GPU. For CPU-only environments, use the Linux binary.

New Features

  • GitLab Merge Request context indexing.

Full Release Notes

## ⚠️ Notice

* The Tabby Docker image now requires an NVIDIA GPU. For CPU-only environments, use the Linux binary.

## 🚀 Features

* Support indexing GitLab Merge Request as Context. [#4227](https://github.com/TabbyML/tabby/pull/4227)

## 🧰 Fixed and Improvements

* Use CUDA 12 image as base image by default. [#4235](https://github.com/TabbyML/tabby/pull/4235)
* Leverage the Answer Engine logic to enrich the context when generating new pages, improving page quality. [#4237](https://github.com/TabbyML/tabby/pull/4237)
* Improve the model configuration details on the System page. [#4236](https://github.com/TabbyML/tabby/pull/4236)
* Resolve the flickering of buttons within code snippets in a chat response during answer generation. [#4233](https://github.com/TabbyML/tabby/pull/4233)
* Set the member filter bar always fixed at the top of the Reports page.[#4232](https://github.com/TabbyML/tabby/pull/4232)
* Resolve the issue when loading a multi-part model from local.[#4302](https://github.com/TabbyML/tabby/pull/4302)

## 💫 New Contributors

* @petarjuki7 made their first contribution in [#4265](https://github.com/TabbyML/tabby/pull/4265)

**Full Changelog**: https://github.com/TabbyML/tabby/compare/v0.29.0...v0.30.0