v0.12.1-rc.0

Release 0.12.1-rc.0

aim-downloader@0.12.1-rc.0
http-api-bindings@0.12.1-rc.0
llama-cpp-server@0.12.1-rc.0
ollama-api-bindings@0.12.1-rc.0
tabby@0.12.1-rc.0
tabby-common@0.12.1-rc.0
tabby-db@0.12.1-rc.0
tabby-db-macros@0.12.1-rc.0
tabby-download@0.12.1-rc.0
tabby-git@0.12.1-rc.0
tabby-inference@0.12.1-rc.0
tabby-scheduler@0.12.1-rc.0
tabby-schema@0.12.1-rc.0
tabby-webserver@0.12.1-rc.0

Generated by cargo-workspaces

v0.12.0

🚀 Features

• Support Gitlab SSO
• Support connect with Self-Hosted Github / Gitlab
• Repository Context is now utilizied in "Code Browser" as well

🧰 Fixed and Improvements

• llama-server from llama.cpp is now distributed as an individual binary, allowing for more flexible configuration
• HTTP API is out of experimental - you can connect tabby to models through HTTP API. Right now following APIs are supported:
  • llama.cpp
  • ollama
  • mistral / codestral
  • openai

💫 New Contributors

• @andreabak made their first contribution in #2069
• @vovochka404 made their first contribution in #2114
• @godsarmy made their first contribution in #2203
• @Geremia made their first contribution in #2256

Full Changelog: v0.11.0...v0.12.0

v0.12.0-rc.5

v0.12.0-rc.5

v0.12.0-rc.4

Release 0.12.0-rc.4

aim-downloader@0.12.0-rc.4
http-api-bindings@0.12.0-rc.4
llama-cpp-server@0.12.0-rc.4
ollama-api-bindings@0.12.0-rc.4
tabby@0.12.0-rc.4
tabby-common@0.12.0-rc.4
tabby-db@0.12.0-rc.4
tabby-db-macros@0.12.0-rc.4
tabby-download@0.12.0-rc.4
tabby-git@0.12.0-rc.4
tabby-inference@0.12.0-rc.4
tabby-scheduler@0.12.0-rc.4
tabby-schema@0.12.0-rc.4
tabby-webserver@0.12.0-rc.4

Generated by cargo-workspaces

v0.12.0-rc.3

v0.12.0-rc.3

v0.12.0-rc.2

v0.12.0-rc.2

v0.12.0-rc.1

v0.12.0-rc.1

v0.12.0-rc.0

v0.12.0-rc.0

v0.11.1

For release notes of the v0.11 minor version, please refer to v0.11.0.

🧰 Fixes and Improvements

• Fixed the display of files with special characters in their paths. (#2081)
• Resolved the issue where non-admin users were unable to see the repository in the Code Browser. (#2110)

v0.11.0

⚠️ Notice

• BREAKING: The --webserver flag is now enabled by default in tabby serve. To turn off the webserver and only use OSS features, use the --no-webserver flag.
• The /v1beta/chat/completions endpoint has been moved to /v1/chat/completions, while the old endpoint is still available for backward compatibility.

🚀 Features

• Added storage usage statistics in the System page.
  

• Added support for integrating repositories from GitHub and GitLab using personal access tokens.

  

• Introduced a new Activities page to view user activities.

  

• Included an Ask Tabby feature in the source code browser to provide in-context help from AI.

  

• Upgraded llama.cpp to version b2715.

• Implemented incremental indexing for faster repository context updates.

🧰 Fixes and Improvements

• Changed the default model filename from q8_0.v2.gguf to model.gguf in MODEL_SPEC.md.
• Excluded activities from deactivated users in reports.

💫 New Contributors

• @karaketir16 made their first contribution in #1902
• @JC-comp made their first contribution in #1903
• @dependabot made their first contribution in #1921
• @winstxnhdw made their first contribution in #2030
• @idushii made their first contribution in #2003
• @nuke-web3 made their first contribution in #2035
• @nopperl made their first contribution in #2055

Full Changelog: v0.10.0...v0.11.0