MMFlash paper: lossless speculative decoding speedups up to 3.58× for vision-language models

rsasaki0109 · x · 2026-11-16

A new Hugging Face paper page presents MMFlash, a speculative decoding framework for vision-language models.

Related event: MMFlash speeds up vision-language models up to 3.58x with lossless speculative decoding(3 posts)→

Original post →

More from Research

Research channel →