Round 2! @kmtracey helped install our 2nd GPU to run local #llm models at the @caktusgroup office along with Gerald and @tobiasmcnulty. We are using vllm over Tailscale with pi.dev for coding and LibreChat for a simple web interface!
Round 2! @kmtracey helped install our 2nd GPU to run local #llm models at the @caktusgroup office along with Gerald and ...