ZYWNB666
ZYWNB666
You don't need to deploy multiple instances; you just need to create another secret and specify this secret when setting up the StorageClass to achieve what you want
For the same problem, we need to manually upload the model file to the minio bucket, and now the bucket becomes unrecognizable, which is very inconvenient
I also encountered this problem. Have you solved it 
I have the same doubt
I also want to know the answer to this question, you can apply for multiple gpu resources when you do not use mps, but you cannot apply for multiple gpu...
@klueska Dude, do you have time to look at my problem?
@elezar Dude, do you have time to look at my problem?
First, the value of default_runtime_name in containerd should be nvidia. After setting the value, you need to follow the documentation to enable GPU Support in Kubernetes Just one command. ```bash...
I still have some questions 1. If I do not set the value of default_runtime_name in containerd to nvidia, the pod will not be able to apply for a gpu....
> I still have some questions > > 1. If I do not set the value of default_runtime_name in containerd to nvidia, the pod will not be able to apply...