DFlash 2 block-diffusion drafter gives Qwen3.8-27B up to 8× speedups
Benchmarking Inco AI's DFlash 2 block-diffusion drafter in a llama.cpp PR build on Qwen3.8-27B shows a 2.26× speedup on real coding prompts, 4.68× with an n-gram drafter, and up to 8× in specific cases. Speculative decoding leaves output provably unchanged, so users get near-doubled throughput without retraining or touching the base model. It's Apache 2.0 and open on GitHub.