It turns out that you can speed up Google's @googlegemma 's DiffusionGemma 3-10x by…
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
It turns out that you can speed up Google's @googlegemma 's DiffusionGemma 3-10x by borrowing some of Jev's ideas. The @GoogleDeepMind model is working off probabilities already - if you fix the structured tokens of the response in place, you can drastically reduce the amount of work you do and get answers in far less time. I implemented this for diffgemma, but it could probably find its way into vLLM as well: https://github.com/mmastrac/diffgemma/pull/21
Posted by Matt Mastracci (7.9k followers) 2 days ago · 226 likes · 12.8k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: diffgemma.
More dev work like this
- Hallmark has been installed 50k+ times! — @nutlope
- Your AI coding agents need a workflow, not more babysitting. — @DanKornas
- Register by October 7 and save >> https://bit.ly/4vkntyD — @linuxfoundation
- Nimble is able to process images! — @madiator
- Your agent already solved this. Finding the session is the problem. — @DanKornas
- Trains your own large language model from scratch using plain PyTorch. — @tom_doerr
- gpt 5.6 terra = gpt 6 astra — @notjazii
- your rtx 3060 was running bonsai 2 at 26 tok/s this morning and now does 40 tok/s, i… — @sudoingX
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:39 UTC. Full method.