1:00:35

Building the Foundations of Self-Improving LLM Agents

24:21

Running State-of-Art Gen AI Models on-Device with NPU Acceleration - Felix Baum, Qualcomm

2:09:48

C can do this too and it's faster than Python

1:01:54

Develop AI agents with Semantic Kernel - Jakob Ehn - NDC Oslo 2024

22:30

vLLM: Easy, Fast, and Cheap LLM Serving, Woosuk Kwon, UC Berkeley

39:33

AI Revolution: What Nobody Else Is Seeing

33:29

How does batching work on modern GPUs?

3:31:24

Deep Dive into LLMs like ChatGPT