⚠️ Notice

• Starting from this version, we are utilizing websockets for features that require streaming (e.g., Answer Engine and Chat Side Panel). If you are deploying tabby behind a reverse proxy, you may need to configure the proxy to support websockets.

🚀 Features

• Discussion threads in the Answer Engine are now persisted, allowing users to share threads with others.

🧰 Fixed and Improvements

• Fixed an issue where the llama-server subprocess was not being reused when reusing a model for Chat / Completion together (e.g., Codestral-22B) with the local model backend.
• Updated llama.cpp to version b3571 to support the jina series embedding models.

💫 New Contributors

• @richginsberg made their first contribution in https://github.com/TabbyML/tabby/pull/2738
• @VladislavNekto made their first contribution in https://github.com/TabbyML/tabby/pull/2804
• @Sherlock113 made their first contribution in https://github.com/TabbyML/tabby/pull/2809
• @zwpaper made their first contribution in https://github.com/TabbyML/tabby/pull/2812
• @cclauss made their first contribution in https://github.com/TabbyML/tabby/pull/2832
• @richard-jfc made their first contribution in https://github.com/TabbyML/tabby/pull/2835

Full Changelog: https://github.com/TabbyML/tabby/compare/v0.15.0...v0.16.1