Accelerating Gemma 4: faster inference with multi-token prediction drafters
(blog.google)
590 points
by amrrs
19 hours ago |
277 comments
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()
()