Welp. I tried to get vLLM installed and I couldn't. I got ollama installed on a cheap VPS and it was practically unusable. Practically the smallest LLM you will find will take four minutes to put one word to the console, if you're not using a GPU.
I guess I'll be using cloud-based LLMs for the time being.
Embed Notice
HTML Code
Corresponding Notice
- Embed this notice
kuteboiCoder (kuteboicoder@subs4social.xyz)'s status on Friday, 16-Aug-2024 14:06:26 JSTkuteboiCoder