DFlash Collection Block Diffusion for Flash Speculative Decoding • 23 items • Updated Jun 28 • 156
🚀 Qwen-MTP Collection ⚡ MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy. • 9 items • Updated Jun 29 • 37
MiniCPM-o & MiniCPM-V Collection Multimodal models with leading performance. • 32 items • Updated 4 days ago • 86