Running and Fine-tuning Open Source LLMs on Google Kubernetes Engine

Dive into the world of open-source Large Language Models (LLMs) with this 32-minute conference talk from the Linux Foundation. Learn how to deploy and fine-tune LLMs on Google Kubernetes Engine (GKE) through hands-on demonstrations. Explore containerization techniques, discover optimal GKE cluster configurations for TPU/GPU acceleration, and gain insights into practical fine-tuning approaches tailored to specific use cases. Walk away equipped with code examples and blueprints to kickstart your own LLM-powered projects on Google Cloud infrastructure.