Replying to Avatar Quentin

AI moderation and the relay are the two main components that generate the highest CPU usage in the infrastructure (16 GB RAM, 8 vCores, 5 million events, 400,000 hosted files, ~4,000 nostr addresses).
Avatar
imp0stor 4mo ago

Does it support gpu acceleration for the ai tasks and can that be pointed to a separate endpoint or does it need to be local?

Those specs are not too outrageous.

Reply to this note

Please Login to reply.

Discussion

Avatar
Quentin 4mo ago

Yes, it supoort gpu acceleration and yes, it can be pointed to a separate endpoint 🥳💪

Avatar
imp0stor 4mo ago

Might be cool to add direct ollama chat bot integration too