27:41

Understanding Mamba and State Space Models

51:56

Serve a Custom LLM for Over 100 Customers

36:12

Deep Dive: Optimizing LLM inference

46:51

Fine tuning LLMs for Memorization

17:27

Real-Time Speech-to-Text & Speaker Identification using Whisper, Vosk & Pyannote (Open-Source)

12:46

Speculative Decoding: When Two LLMs are Faster than One

1:09:25

Lecture 22: Hacker's Guide to Speculative Decoding in VLLM

54:59

Test Time Compute, Part 1: Sampling and Chain of Thought