Parrot: Efficient Serving of LLM-based Applications with Semantic Variable
Offered By: USENIX via YouTube
Course Description
Overview
Explore a groundbreaking conference talk on Parrot, an innovative LLM service system designed to enhance the end-to-end performance of LLM-based applications. Discover how Semantic Variable, a unified abstraction, exposes application-level knowledge to public LLM services, enabling more efficient programming of AI agents and co-pilots. Learn about the potential for order-of-magnitude improvements in popular LLM application use cases through advanced data flow analysis and optimization techniques. Gain insights into the future of LLM service architecture and its impact on diverse tenant applications with complex workflows.
Syllabus
OSDI '24 - Parrot: Efficient Serving of LLM-based Applications with Semantic Variable
Taught by
USENIX
Related Courses
Using MPT-7B in Hugging Face and LangChainJames Briggs via YouTube Intelligence Augmentation
TEDx via YouTube AI Skills: Basic and Advanced Techniques in Machine Learning
Delft University of Technology via edX LangChain AI Handbook
Pinecone via Independent Hiring AI Agents - Implementing GPT-4 for Content Creation and Analysis
All About AI via YouTube