v0.8.0

⚠️ Notice

• Due to format changes, re-executing tabby scheduler --now is required to ensure that Code Browser functions properly.

🚀 Features

• Introducing a preview release of the Code Browser, featuring visualization of code snippets utilized for code completion in inference.

• Added a Windows CPU binary distribution.
• Added a Linux ROCm (AMD GPU) binary distribution.

🧰 Fixes and Improvements

• Fixed an issue with cached permanent redirection in certain browsers (e.g., Chrome) when the --webserver flag is disabled.
• Introduced the TABBY_MODEL_CACHE_ROOT environment variable to individually override the model cache directory.
• The /v1beta/chat/completions API endpoint is now compatible with OpenAI's chat completion API.
• Models from our official registry can now be referred to without the TabbyML prefix. Therefore, for the model TabbyML/CodeLlama-7B, you can simply refer to it as CodeLlama-7B everywhere.

💫 New Contributors

• @cljoly made their first contribution in #1017
• @jasonharrison made their first contribution in #1021
• @cromefire made their first contribution in #1012
• @Blackclaws made their first contribution in #1028
• @ichDaheim made their first contribution in #1045
• @hduelme made their first contribution in #1095
• @concretevitamin made their first contribution in #1103
• @Lash-L made their first contribution in #1104
• @appetrosyan made their first contribution in #1251
• @anoldguy made their first contribution in #1244
• @fbagnol made their first contribution in #1243
• @laleph made their first contribution in #1278

Full Changelog: v0.7.0...v0.8.0