llama.cpp/vendor
Eric Curtin 79069a05bb New llama-run
- Added readline.cpp include
- Created run_chat_mode():
  - Initializes readline with command history
  - Maintains conversation history
  - Applies chat templates to format messages
  - Submits completion tasks to the server queue
  - Displays assistant responses interactively

Signed-off-by: Eric Curtin <eric.curtin@docker.com>
2025-12-01 20:33:45 +00:00
..
cpp-httplib cmake : add option to build and link LibreSSL (#17552) 2025-11-30 22:14:32 +01:00
miniaudio vendors: update miniaudio version (#16212) 2025-09-25 23:38:10 +08:00
minja sync: minja (glm 4.6 & minmax m2 templates) (#16949) 2025-11-03 07:33:56 +02:00
nlohmann sync : vendor (#13901) 2025-05-30 16:25:45 +03:00
readline.cpp New llama-run 2025-12-01 20:33:45 +00:00
sheredom server: introduce API for serving / loading / unloading multiple models (#17470) 2025-12-01 19:41:04 +01:00
stb sync : vendor (#13901) 2025-05-30 16:25:45 +03:00