Headline
- Llama.cpp now also works on non-streaming mode (@danielholanda)
- Both
completionsandchat/completionsnow returnusage(@danielholanda)
Documentation
- Added instructions on how to integrate Lemonade Server with your application in languages including Python, C++, Java, C#, Node.js, Go, Ruby, Rust, and PHP (@danielholanda )
Bugs Fixed
- Hybrid installation also works if CPU check fails (@ramkrishna2910)
- Fixed website publishing script (@jeremyfowers)
- Patch the supported devices list (@jeremyfowers)