🤗 Hugging Cast S2E3 - Deploying LLMs on Google Cloud
Hugging Cast is a live show about building AI with open source.
In this episode, Philipp, Alvaro and Jeff demo 3 new ways to deploy open models on Google Cloud:
1️⃣ with Hugging Face Inference Endpoints
2️⃣ within Google Cloud Model Garden on Vertex AI or GKE
3️⃣ using TGI for TPU in our new library optimum-tpu