gpustack / llama-box

LLM inference server implementation based on llama.cpp.
MIT License
34 stars 5 forks source link

Show parameters used in INFO log #8

Open pengjiang80 opened 3 days ago

pengjiang80 commented 3 days ago

Parameters used with llama-box are shown in the log by default; it's better to show them in the INFO log. It will be helpful for GPUStack users to know what parameters are used.

thxCode commented 1 day ago

https://github.com/gpustack/llama-box/releases/tag/v0.0.80