AI Briefing#dflash
The latest AI and developer news about #dflash, with the original source and a short summary.
The latest AI and developer news about #dflash, with the original source and a short summary.
The draft models combine a five-layer DFlash backbone with a learned bigram selector to propose multiple candidate continuations for target-model verification.
Xiaomi has released the MiMo-V2.5-DFlash model weights, which have a large number of parameters, via Hugging Face.
DFlash technology, developed jointly by Z Lab and Modal, achieved LLM inference performance far superior to existing MTP methods.
The BeeLlama v0.2.0 update improves inference speed for Qwen 3.6 and Gemma 4 models by up to 4.9x.
The BeeLlama v0.2.0 update significantly boosts inference speed for Qwen and Gemma models through DFlash optimization.
ExLlamaV3 has added Gemma 4 support, DFlash optimization, and bug fixes.
z-lab has released the DFlash drafter model and paper for Gemma 4.
A UCSD research team achieved an average 3.13x speedup with DFlash on Google TPU v5p.
z-lab has released the DFlash version of Gemma 4 31B-it on Hugging Face.
DFlash for Qwen3.5-35B-A3B was confirmed running on an RTX 2080 SUPER 8GB.
DFlash doesn't speed up as much as expected with MoE, quantization, concurrent use, and long context.
On an M2 Max, DTree showed MLX results **1.07x** faster than DFlash.
With DFlash in oMLX 0.3.5 RC1, Qwen3.5 27B went from 9 to 22 T/S on a Mac M5 Max.