I run python3 -m llama_cpp.server in order to call the API from my scripts. I'd like to implement prompt caching (like I can do in llama-cpp), but the command line options that work for llama-cpp ...

a command line argument or command line arguments for python scenes; a command line argument that can be used in all scenes, such as -d for data, which could be followed by strings; php scenes (file ...

To run a Python script with the py launcher, simply substitute py and its command-line switches for python or python3. ... Any arguments provided after the version are passed along as per usual.