LLM Streaming

Open slumdev88 opened this issue 3 months ago • 3 comments

Hey guys, I've been playing around with my own app that I built from scratch and i have been over optimizing with codex. Compared to Voiceink, my LLM processing step is about half the time (using the same model). There's probably a number of factors that contribute to this, but I think one of the key factors is the implementation of LLM streaming. Something for you to look into.

Sep 17 '25 23:09 slumdev88