Joe Chen

finally server was up but still with error ```shell INFO: 192.168.31.32:53875 - "GET /v1/models HTTP/1.1" 200 OK INFO: 192.168.31.32:53895 - "GET /v1/models HTTP/1.1" 200 OK INFO: 192.168.31.32:53900 - "GET /v1/models...

may i create a PR to make mutiple incident event show at same time ?

i think show multiple incident and incident history are two things. show multiple incident is a indicator of current ongoing incidents.user can get insigh what and how many incidents current...

> Going from 1:1 to 1:n is likely fine. The current UI + DB layout is not optimised for this though. > > Make sure that: > > * you...

i have done this in #4986 , if need any further adjustments or specific terms included, let me know

https://github.com/ggml-org/llama.cpp/pull/9510

and i'm using text 2 text model:https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-1M and embedding model https://huggingface.co/nomic-ai/nomic-embed-text-v1.5

https://github.com/ggml-org/llama.cpp/issues/11988 i fond this

solved

add openai like API support i think is enough, most saas or self hosted llm are support that format api