GitLab

Co-authored-by: Michael Yang <mxyng@pm.me>

This focuses on Windows first, but coudl be used for Mac
and possibly linux in the future.

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

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

* remove c code
* pack llama.cpp
* use request context for llama_cpp
* let llama_cpp decide the number of threads to use
* stop llama runner when app stops
* remove sample count and duration metrics
* use go generate to get libraries
* tmp dir for running llm

- read runner options from map to see what was specified explicitly and overwrite zero values

Co-authored-by: Patrick Devine <pdevine@sonic.net>