This message was deleted.

Hi @James-Andrew Sarmiento, sorry for the late reply. Do you mean Google CloudRun? I assume that this question is about running bentoml on cloudrun. You can use bentoctl

cloud-run-deploy

to deploy a bentoml to Cloud Run As of supporting on accelerator, it varies from use-case to use-case You can use either GPU or CPU to run inference with BentoML. As about other accelerator, such as XPU, TPU, OpenVino, we are currently don’t have support for those just yet