Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Watch a technical workshop demonstrating enterprise-ready generative AI workflows using NVIDIA and Canonical tools. Explore how to leverage the NVIDIA NGC Catalog and NVIDIA AI Enterprise suite for implementing scalable AI solutions with Kubernetes and KServe integration. Follow along as experts showcase deploying Meta's Llama 3.1 8b model, performing inference with NVIDIA NIM, implementing dynamic scaling through KServe, and utilizing PEFT techniques with LoRA adapters for multiple fine-tuned model versions on a single Kubernetes cluster. Learn practical deployment strategies that can be replicated using widely available open-source resources and community-supported tools for model development and deployment in enterprise environments.
