Modal Labs released state-of-the-art DFlash speculators for Qwen 3.5 and Qwen 3.6 models on Hugging Face, achieving 5-20% additional speedups and enabling Qwen 3.5 122B-A10B to run at over 1000 tok/s …
Modal and Z Lab released DFlash, a speculative decoding model for Qwen 3.5 397B-A17B, achieving over 4.3x throughput versus baseline and 1.5x versus MTP on HumanEval at concurrency 1. The model uses a…
Jian Chen, Yesheng Liang, and Zhijian Liu integrated Z Lab's DFlash block diffusion speculative decoding method into SGLang, collaborating with Modal and LMSYS. The team reports up to 4.31x higher thr…
Researchers at UC San Diego, led by Hao Zhang, have successfully implemented a diffusion-style speculative decoding method called DFlash on Google TPUs, achieving an average 3.13x increase in tokens p…