The Two Models That Never Met. Both Measured at the Same Depth.
May 01, 2026
Read more Research 
Speculative Decoding for Free: Pairing DFlash with our DFO-Tuned Gemma 4 31B
By • May 09, 2026
z-lab's DFlash drafter was trained against stock Gemma 4 31B. We dropped it on top of our QLoRA fine-tune and it captured 92% of the published speedup with no drafter retraining. Here is the math, the vLLM patch we had to upstream to make it run, and the prod-cutover numbers (~15× faster, ~4× cheaper).
Read Article