mac_ai remote_ramalama_run_model

Runs a model with ramalama, on a remote host

Parameters

base_work_dir

  • The base directory where to store things

path

  • The path to the llama-server binary

port

  • The port number on which llama-cpp should listen

name

  • The name of the model to run

env

  • The env values to set before running ramalama

ngl

  • Number of layers to store in VRAM

  • default value: 99

device

  • Name of the device to pass to the container

unload

  • If True, unloads (stops serving) this model