From the source
Today, we're thrilled to announce that Mercury is available on Azure AI Foundry , bringing the first commercial-scale diffusion large language model (dLLM) to enterprise developers.
This release combines Inception's breakthrough diffusion architecture with Azure's enterprise-ready infrastructure, giving developers access to a model that delivers both exceptional speed and quality.
Built by the team behind foundational AI technologies including Flash Attention, Direct Preference Optimization, and the original diffusion models for images, Mercury represents a fundamental shift in how language models generate text.
Developers on Azure AI Foundry now have access to a model that redefines what's possible in real-time AI applications.
A New Architecture for Language Generation Traditional language models generate text sequentially, one token at a time.
This creates an inherent bottleneck where each token must wait for all previous tokens to be generated.
Mercury uses a diffusion-based architecture to generate multiple tokens in parallel, enabling dramatically faster inference.
The result: Mercury runs up to 10x faster than comparable autoregressive models.
…
