Mercury
The First Commercial-Scale Diffusion LLM
8 followers
The First Commercial-Scale Diffusion LLM
8 followers
Mercury,from Inception Labs, is the first commercial diffusion LLM. Up to 10x faster than autoregressive models, with comparable or better quality on coding tasks.
Flowtica Scribe
Hi everyone!
Check out something very different in the LLM space: Mercury, from Inception Labs. This isn't another autoregressive model like GPT or Llama, it's a diffusion LLM (dLLM), and it's the first commercial-scale one.
The big deal here is speed. Diffusion models are how AI generates images (think Midjourney, Stable Diffusion), but applying them to text is new. Mercury is up to 10x faster than comparable, speed-optimized autoregressive models, and can hit over 1000 tokens/second on an NVIDIA H100.
They have a playground to test in Mercury Coder, and they offer API access and on-premise deployments for enterprise clients. A chat model is in closed beta.