DIFFUSION-MODELS
2 items
2 posts
Blog
DiffusionGemma: Google Bets Diffusion Can Make Text Generation 4x FasterGoogle released DiffusionGemma today, a 26B MoE open model that generates entire 256-token blocks in parallel instead of one token at a time. Here is what that means for latency, local inference, and the post-autoregressive landscape.
Blog
Diffusion Language Models: How Mercury Changed the LLM Speed GameInception Labs launched Mercury, the first commercial-grade diffusion large language model. It generates over 1,000 tokens per second on standard Nvidia hardware by replacing autoregressive generation with a coarse-to-fine diffusion process.
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever