Nvidia's Record Revenue 📈 // OpenAI's News Corp Deal 📰 // Your Transformer is Secretly Linear 🔍

Nvidia's Q1 revenue up 262% to $26.0B, beating estimates. OpenAI's News Corp deal licenses content from WSJ, New York Post and more. PyramidInfer compresses KV cache to save memory during inference for Large Language Models. Your Transformer is Secretly Linear challenges our existing understanding of transformer architectures. Contact:  [email protected] Timestamps: 00:34 Introduction 01:55 Nvidia's Q1 revenue up 262% to $26.0B, beating estimates 03:23 OpenAI’s News Corp deal licenses content from WSJ, New York Post, and more 04:57 Systematically Improving Your RAG 06:18 Fake sponsor 08:17 PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference 09:49 Reducing Transformer Key-Value Cache Size with Cross-Layer Attention 11:48 Your Transformer is Secretly Linear 13:26 Outro