llama.cpp/vendor/readline.cpp/include
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
..
readline New llama-run 2025-12-01 20:33:45 +00:00