GPT-Fast - blazingly fast inference with PyTorch (w/ Horace He) Published 2024-03-07 Download video MP4 360p Download video MP4 720p Recommendations 1:11:46 How does Groq LPU work? (w/ Head of Silicon Igor Arsovski!) 55:08 Lucas Beyer (Google DeepMind) - Convergence of Vision & Language 54:50 Jeremy Howard - answer.ai, what is wrong with the academia and industry 51:06 Fine-tune Multi-modal LLaVA Vision and Language Models 06:30 this is the fastest AI chip in the world: Groq explained 27:41 Understanding Mamba and State Space Models 1:56:20 Let's build GPT: from scratch, in code, spelled out. 19:21 How I Made AI Assistants Do My Work For Me: CrewAI 06:10 The Era of 1-bit LLMs by Microsoft | AI Paper Explained 11:57 What is PyTorch? (Machine/Deep Learning) 09:40 5 Coding Projects That Give You An UNFAIR Advantage 59:48 [1hr Talk] Intro to Large Language Models 1:05:32 François Chollet - Creating Keras 3 52:43 OpenAI DALL-E 3 with James Betker (1st author) 11:42 The architecture of mixtral8x7b - What is MoE(Mixture of experts) ? 09:53 "okay, but I want GPT to perform 10x for my specific use case" - Here is how 1:11:41 Stanford CS25: V2 I Introduction to Transformers w/ Andrej Karpathy 53:52 GPT-4 - How does it work, and how do I build apps with it? - CS50 Tech Talk 07:42 DeepMind’s New AI Makes Games From Scratch! 07:05 How I’d learn ML in 2024 (if I could start over)