Error: CUDA error: CUDA-capable device(s) is/are busy or unavailable

I have 15 production endpoints deployed using Runpod and today they started to raise this error randomly. Do you know what is happening? I am worried about this because it generating a bad experience to the users of my product. Thanks

Continue the conversation

Join the Discord to ask follow-up questions and connect with the community

Runpod

We're a community of enthusiasts, engineers, and enterprises, all sharing insights on AI, Machine Learning and GPUs!

21,906 Members

Join

Error: CUDA error: CUDA-capable device(s) is/are busy or unavailable

Error: CUDA error: CUDA-capable device(s) is/are busy or unavailable

Continue the conversation

Runpod

Continue the conversation

Runpod

Similar Threads