GitLab

By default builds will now produce non-debug and non-verbose binaries.
To enable verbose logs in llama.cpp and debug symbols in the
native code, set `CGO_CFLAGS=-g`

The default thread count logic was broken and resulted in 2x the number
of threads as it should on a hyperthreading CPU
resulting in thrashing and poor performance.

Run the server.cpp directly inside the Go runtime via cgo
while retaining the LLM Go abstractions.