Join this workshop with NVIDIA to learn how to build LLM systems customized to your domain-specific applications. We will discuss strategies for:

• Getting the best results with an LLM, including using Retrieval Augmented Generation (RAG) and Parameter-Efficient Fine-Tuning (PEFT).
• Preparing datasets, including incorporating synthetic data generation and identifying input/output pairs in existing workflows.
• Optimizing LLMs for lower-latency and higher-throughput inference to reduce compute needs.