Deploying and managing open models with Hugging Face TGI on GKE is great, but how to autoscale? In this video with @boredabdel.bsky.social, we show you how to use TGI queue size as a scaling signal.
Video 👉 www.youtube.com/watch?v=QjLZ...
Playlist 👉 www.youtube.com/playlist?lis...
