GitLab

This should resolve a number of memory leak and stability defects by allowing
us to isolate llama.cpp in a separate process and shutdown when idle, and
gracefully restart if it has problems.  This also serves as a first step to be
able to run multiple copies to support multiple models concurrently.

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

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

* Support cuda build in Windows
* Enable dynamic NumGPU allocation for Windows

* 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