DFlash uses a lightweight block diffusion model as a drafter for speculative decoding, conditioned to predict future token blocks based on the K/V cache extracted directly from the target LLM during inference. Reportedly achieves ~6.17x lossless speed-up for Qwen3-8B.
Findings
This is where I'll be saving links to interesting things I stumble across on the internet. You'll find cool research papers on LLMs that have caught my attention, fascinating tech discoveries, and other curiosities worth preserving.