

Graphs for HPC and LLMs
Oct 29, 2024
Maciej Besta, a senior researcher at the Scalable Parallel Computing Lab, discusses the cutting-edge intersection of graph theory and high-performance computing. He explores how graph structures enhance large language models through APIs and hypergraphs. The conversation covers challenges in graph databases, the LPG2Vec encoder for data embedding, and advancements in prompt engineering to optimize problem-solving capabilities. Besta also dives into methodologies like chain of thought and the complexities of graph theory in developing efficient language models.
Chapters
Transcript
Episode notes
1 2 3 4 5 6 7
Intro
00:00 • 2min
Graph Data Structures and Performance Challenges
02:26 • 7min
The Multifaceted World of Graph Data Structures and Their Applications
09:26 • 5min
Exploring the Varied Landscape of Graph Databases
13:59 • 4min
Connecting Graph Science and LLMs
17:53 • 21min
Mastering Prompt Engineering
38:56 • 9min
Exploring Complexity in Graph Theory and Language Models
47:46 • 4min