The "24gb pro" gpu availability show "highly available", but when the docker is mounted on any RTX4090 EU-RO-1 they are simply all being throttled. Has been like so since yesterday as observed. It's kinda annoying as this prevents the algorithm to seek for lower priority gpu choices even though the runner cannot serve any traffic.
Continue the conversation
Join the Discord to ask follow-up questions and connect with the community
R
Runpod
We're a community of enthusiasts, engineers, and enterprises, all sharing insights on AI, Machine Learning and GPUs!