Tag
提出DCOCO（DFlash Contextual Corrector），一种轻量级机制，在保持并行草稿生成的同时恢复块内上下文依赖，在四个验证器骨干和十个基准上实现最高达6.6倍的推理加速，并在并发服务场景下显著优于现有方法。
Jeeves is a 9B parameter reasoning-enhanced Jev-like decision model that uses a diffusion drafter, achieving higher accuracy on out-of-domain benchmarks compared to previous models like Kev and Jev.
The Lucebox engine now supports running the Qwen3.8-27B model on a single AMD Radeon AI PRO R9700 GPU, achieving up to 227 tok/s on code tasks using the DFlash2 drafter with lossless verification.