GitLab

Cleaning up go package naming

If the system has multiple numa nodes, enable numa support in llama.cpp
If we detect numactl in the path, use that, else use the basic "distribute" mode.

Now that we call the GPU discovery routines many times to
update memory, this splits initial discovery from free memory
updating.

The GPU drivers take a while to update their free memory reporting, so we need
to wait until the values converge with what we're expecting before proceeding
to start another runner in order to get an accurate picture.

A few obvious levels were adjusted, but generally everything mapped to "info" level.

This switches darwin to dynamic loading, and refactors the code now that no
static linking of the library is used on any platform