subprocess llama.cpp server (#401)

* 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

docs/development.md

@@ -1,19 +1,21 @@
 # Development
 
+- Install cmake or (optionally, required tools for GPUs)
+- run `go generate ./...`
+- run `go build .`
+
 Install required tools:
 
 ```
-brew install go
+brew install go cmake gcc
 ```
 
-Enable CGO:
+Get the required libraries:
 
 ```
-export CGO_ENABLED=1
+go generate ./...
 ```
 
-You will also need a C/C++ compiler such as GCC for MacOS and Linux or Mingw-w64 GCC for Windows.
-
 Then build ollama:
 
 ```