Daniel Hiltgen 58d95cc9bd Switch back to subprocessing for llama.cpp ...

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.

2024-04-01 16:48:18 -07:00

..

gen_common.sh

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

gen_darwin.sh

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

gen_linux.sh

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

gen_windows.ps1

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

generate_darwin.go

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

generate_linux.go

Code shuffle to clean up the llm dir

2024-01-04 12:12:05 -08:00

generate_windows.go

Code shuffle to clean up the llm dir

2024-01-04 12:12:05 -08:00