Google open-sources speedy DiffusionGemma text diffusion model

Google says that DiffusionGemma can generate more than 1,000 tokens per second when running on a single H100, a server-grade ...

Google's DiffusionGemma generates 256 tokens in parallel and self-corrects as it goes

Google's open-source diffusion language model generates 256 tokens in parallel and self-corrects, hitting 4x speed on one GPU ...
Decrypt

Google's DiffusionGemma AI Hits 1,000 Tokens Per Second—And It's Free

DiffusionGemma hits 1,000 tokens per second by ditching word-by-word generation entirely. It just doesn't run on most ...

DiffusionGemma is Google's fastest AI yet, but it comes with a big trade-off

Google's DiffusionGemma takes a new approach to AI text generation, focusing on speed and parallel processing. But there's a ...

Open-source FLIM Playground could speed reproducible analysis of complex cell images

Modern fluorescence microscopy can generate images of living cells as stunning to look at as they are informative to study. For techniques like fluorescence lifetime imaging microscopy (FLIM), those ...