#1: Enable Scale-to-Zero
Enable scale-to-zero in Model Garden to automatically power down your GPU instances when there are no active incoming requests.
Model Garden docs ↓
https://cloud.google.com/model-garden?e=48754805
Google Cloud Model Garden adds scale-to-zero to power down idle GPUs
AISummary
Google Cloud Model Garden now lets users enable scale-to-zero to automatically shut down GPU instances when no incoming requests are active. The feature is presented as a way to avoid paying for idle GPU capacity.
Post on XView on X
@GoogleCloudTech
A reply · the post it answers
Source: Google Cloud Tech · x.comPublished · added here