v0.14.0-rc.1

v0.14.0-rc.1

v0.14.0-rc.0

v0.14.0-rc.0

v0.13.1

⚠️ Notice

• This is a patch release, please also check the full release note for 0.13.

🧰 Fixed and Improvements

• Bump llama.cpp version to b3334, supporting Deepseek V2 series models.
• Turn on fast attention for Qwen2-1.5B model to fix the quantization error.
• Properly set number of GPU layers (to zero) when device is CPU.

v0.13.1-rc.9

v0.13.1-rc.9

v0.13.1-rc.8

v0.13.1-rc.8

v0.13.1-rc.7

v0.13.1-rc.7

v0.13.1-rc.6

v0.13.1-rc.6

v0.13.1-rc.0

v0.13.1-rc.0

v0.13.0

⚠️ Notice

• WizardCoder-3B is no longer supported, for model with low parameter size, consider try Qwen2-1.5B-Instruct

🚀 Features

• Introduced a new Home page featuring the Answer Engine, which activates when the chat model is loaded.

• Enhanced the Answer Engine's context by indexing issues and pull requests.
• Supports web page crawling to further enrich the Answer Engine's context.
• Enabled navigation through various git trees in the git browser.

🧰 Fixed and Improvements

• Turn on sha256 checksum verification for model downloading.
• Added an environment variable TABBY_HUGGINGFACE_HOST_OVERRIDE to override huggingface.co with compatible mirrors (e.g., hf-mirror.com) for model downloading.
• Bumped llama.cpp version to b3166.
• Improved logging for the llama.cpp backend.
• Added support for triggering background jobs in the admin UI.
• Enhanced logging for backend jobs in the admin UI.

💫 New Contributors

• @TennyZhuang made their first contribution in #2355
• @woutermans made their first contribution in #2378

Full Changelog: v0.12.0...v0.13.0

v0.13.0-rc.4

v0.13.0-rc.4