Google has made enhancements to Google Kubernetes Engine (GKE) to facilitate serving and deploying Gemma, an open generative AI model. Gemma can be easily deployed using Hugging Face, Vertex AI Model Garden, and Kaggle integration. Additionally, Gemma can be served on AI-optimized infrastructure powered by Google Cloud TPUs and GPUs.
•2m read time• From cloud.google.com
Table of contents
Hugging FaceSort: