There is a lot of people with the same problem: ERROR: (gcloud.beta.ai-platform.versions.create) Create Version failed. Bad model detected with error: Model requires more memory than allowed. Please try to decrease the model size and re-deploy. If you continue to experience errors, please contact support. (I am one of those)
For this problem is being recommended to create a Custom Container, however, the process is tedious and there isn't any basic example or boilerplate(PyTorch Serve is an overkilling solution if you don't use Torch).
I think it could be very useful for the community if the Google team provides a preconfigured and basic Docker container with the best libraries for each requirement.
There is a lot of people with the same problem:
ERROR: (gcloud.beta.ai-platform.versions.create) Create Version failed. Bad model detected with error: Model requires more memory than allowed. Please try to decrease the model size and re-deploy. If you continue to experience errors, please contact support.
(I am one of those)For this problem is being recommended to create a Custom Container, however, the process is tedious and there isn't any basic example or boilerplate(PyTorch Serve is an overkilling solution if you don't use Torch).
I think it could be very useful for the community if the Google team provides a preconfigured and basic Docker container with the best libraries for each requirement.
Thank you