Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation Paper • 2502.08690 • Published 10 days ago • 39
view article Article PaliGemma 2 Mix - New Instruction Vision Language Models by Google 3 days ago • 50
Running 1.24k 1.24k The Ultra-Scale Playbook 🌌 The ultimate guide to training LLM on large GPU Clusters