view article Article Profiling in PyTorch (Part 3): Attention is all you profile +2 ariG23498, sergiopaniego, sayakpaul, ror • 3 days ago • 18
Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization Paper • 2510.13554 • Published Oct 15, 2025 • 59
Rope to Nope and Back Again: A New Hybrid Attention Strategy Paper • 2501.18795 • Published Jan 30, 2025 • 13
Running 3.93k The Ultra-Scale Playbook 🌌 3.93k The ultimate guide to training LLM on large GPU Clusters