[Docs]: local inference must be configured to run parallel tasks

[Kangaroux]

Using llama-server with this plugin and --parallel 1, the server gets stuck when trying to spawn a PTY. Raising it to at least --parallel 2 seems to be fine.

I think it's worth calling this out in the docs for those doing local inference

[shekohex]

I have no idea what llama-server has to do with this plugin to be honest.