Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction Paper • 2609.13285 • Published 17 days ago • 81
Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention Paper • 2606.20945 • Published Jun 18 • 81
view article Article Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance tiiuae • May 21, 2025 • 40
ZClip: Adaptive Spike Mitigation for LLM Pre-Training Paper • 2504.02507 • Published Apr 3, 2025 • 90