Optimization Design Patterns

This lab focuses on the design patterns that can be used to optimize the performance of LLMs in various ways. The patterns are categorized into the following main areas:

1. Evaluation on Streaming

2. Caching

3. Prompt Optimization using PromptWizard

4. Long-term Memory Management


Distributed by an MIT license. This hands-on lab was developed by Microsoft AI GBB (Global Black Belt).