Remix.run Logo
dminik 5 hours ago

You can have multiple models served now with loading/unloading with just the server binary.

https://github.com/ggml-org/llama.cpp/blob/master/tools/serv...

speedgoose 4 hours ago | parent [-]

It only lacks the automatic FIFO loading/unloading then. Maybe it will be there in a few weeks.