Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation Paper โข 2511.14993 โข Published Nov 19 โข 226
Running 3.61k The Ultra-Scale Playbook ๐ 3.61k The ultimate guide to training LLM on large GPU Clusters
Benchmarking Optimizers for Large Language Model Pretraining Paper โข 2509.01440 โข Published Sep 1 โข 24