There's also a growing interest on integrating DFlash: https://github.com/ggml-o...

		egeres 17 days ago \| parent \| context \| favorite \| on: Accelerating Gemma 4: faster inference with multi-... There's also a growing interest on integrating DFlash: https://github.com/ggml-org/llama.cpp/issues/21978, I can't wait to see how it will compare against MTP