Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism Paper • 2605.30852 • Published 5 days ago • 7
Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio Paper • 2603.25926 • Published Mar 26 • 8
Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio Paper • 2603.25926 • Published Mar 26 • 8