Wei Zhang 1632dd054e feat(llama-cpp-server): reuse local server for completion and chat (#2812) ... * ✨ support reuse the same server if model id is equaled Signed-off-by: Wei Zhang <kweizh@gmail.com> * 🎨 fix review Signed-off-by: Wei Zhang <kweizh@gmail.com> * 🔨 should compare model in llama cpp server Signed-off-by: Wei Zhang <kweizh@gmail.com> * match case for creating completion and chat Signed-off-by: Wei Zhang <kweizh@gmail.com> * if let case for creating completion and chat Signed-off-by: Wei Zhang <kweizh@gmail.com> * add changelog * rebase && make fix --------- Signed-off-by: Wei Zhang <kweizh@gmail.com> Co-authored-by: Meng Zhang <meng@tabbyml.com>		2024-08-10 22:51:13 -07:00
..
.gitkeep
Features-20240805-162901.yaml	feat(webserver): support persisted thread in answer engine (#2793)	2024-08-09 15:29:19 -07:00
Fixed and Improvements-20240810-221045.yaml	feat(llama-cpp-server): reuse local server for completion and chat (#2812)	2024-08-10 22:51:13 -07:00