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

..

CMakeLists.txt

Switch back to subprocessing for llama.cpp

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

httplib.h

Import server.cpp as of b2356

2024-03-12 13:58:06 -07:00

json.hpp

Import server.cpp as of b2356

2024-03-12 13:58:06 -07:00

server.cpp

Switch back to subprocessing for llama.cpp

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

utils.hpp

add license in file header for vendored llama.cpp code (#3351)

2024-03-26 16:23:23 -04:00