Differences Between Space Hardware Configurations and CPU Upgrade Space's 500 Error Issue

Hello,
I designed a backend for an LLM Leaderboard. The issue is that while it runs on the same space with CPU basic and Nvidia T4 medium, it doesn’t work on CPU Upgrade. After the model loads, it gives a connection error during the inference phase. I don’t understand why it’s not working on a resource with more RAM and CPU when it works fine on a lower resource. It’s a very frustrating situation. Is there anyone who can help?

here is the space link: Backend - a Hugging Face Space by LLM-Beetle

2 Likes

Maybe same here…

Likely same issue, I am using HF space to prepare dataset, using the CPU Upgrade for 4 spaces and while 2 of them runs just happy, the other 2 with the same CPU Upgrade gets throttled and crash after a certain time perriod

1 Like

@meganariley @not-lain Paid space error issue. Apart from the Tonic 500 error, there seems to be a Spaces error that occurs after a certain amount of time. I’ve seen other complaints about the same thing.

Perhaps related: