Attention is all you need (Transformer) - Model explanation (including math), Inference and Training
2:59:24
Coding a Transformer from scratch on PyTorch, with full explanation, training and inference.
57:45
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
2:11:12
How I use LLMs
27:12
Variational Autoencoder - Model, ELBO, loss function and maths explained easily!
44:06
LLM inference optimization: Architecture, KV cache and Flash attention
36:16
The math behind Attention: Keys, Queries, and Values matrices
7:38:18
Flash Attention derived and coded from first principles with Triton (Python)
54:52