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

..

getstarted_nonwindows.go

Implement new Go based Desktop app

2024-02-15 05:56:45 +00:00

getstarted_windows.go

Implement new Go based Desktop app

2024-02-15 05:56:45 +00:00

lifecycle.go

change github.com/jmorganca/ollama to github.com/ollama/ollama (#3347)

2024-03-26 13:04:17 -07:00

logging_nonwindows.go

Implement new Go based Desktop app

2024-02-15 05:56:45 +00:00

logging_windows.go

Fix view logs menu

2024-02-16 15:42:53 -08:00

logging.go

Implement new Go based Desktop app

2024-02-15 05:56:45 +00:00

paths.go

Implement new Go based Desktop app

2024-02-15 05:56:45 +00:00

server_unix.go

Implement new Go based Desktop app

2024-02-15 05:56:45 +00:00

server_windows.go

Implement new Go based Desktop app

2024-02-15 05:56:45 +00:00

server.go

Switch back to subprocessing for llama.cpp

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

updater_nonwindows.go

Implement new Go based Desktop app

2024-02-15 05:56:45 +00:00

updater_windows.go

clean up some logging

2024-02-15 14:56:55 -08:00

updater.go

change github.com/jmorganca/ollama to github.com/ollama/ollama (#3347)

2024-03-26 13:04:17 -07:00