Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters Paper • 2408.04093 • Published Aug 7 • 4
GoldFinch: High Performance RWKV/Transformer Hybrid with Linear Pre-Fill and Extreme KV-Cache Compression Paper • 2407.12077 • Published Jul 16 • 54
Simple and Scalable Strategies to Continually Pre-train Large Language Models Paper • 2403.08763 • Published Mar 13 • 49