Story

Release highlights

• Kimi-K3 performance push : a major optimization effort for Kimi-K3 across the stack — Decode Context Parallel (DCP) support , fused FlashKDA decode and prefi...
• DeepSeek V4 : sparse MLA now works end-to-end for plain decode, MTP, and DSpark speculative decoding , joined by AMD Quark NVFP4 support , reasoning-effort p...
• Speculative decoding advances : DFlash2 with local convolution and a candidate selector , DSpark confidence-scheduled verification , and async scheduling aut...