Post

Inception on X: "We are excited to introduce Mercury, the first commercial-grade diffusion large language model (dLLM)! dLLMs push the frontier of intelligence and speed with parallel, coarse-to-fine text generation."

We are excited to introduce Mercury, the first commercial-grade diffusion large language model (dLLM)! dLLMs push the frontier of intelligence and speed with parallel, coarse-to-fine text generation.

00:00
Mercury Coder diffusion large language models match the performance of frontier speed-optimized models like GPT-4o Mini and Claude 3.5 Haiku while running up to 10x faster.
We achieve over 1000 tokens/second on NVIDIA H100s. Blazing fast generations without specialized chips!
On Copilot Arena, developers consistently prefer Mercury’s generations. It ranks #1 on speed and #2 on quality. Mercury is the fastest code LLM on the market.

00:00
If you got curious by the is diffusion large language model but realized it’s not open source: it’s your lucky day 🍀 LLaDA 8B - an open source apache 2 large diffusion language model is also just out! ✨ competitive with LLaMA 3 8B
LLaDA (the first Large Language Diffusion Model) is *just* out 💥 and I've built a demo, try out now 👨‍💻 It's mesmerizing to watch the diffusion process 🌀, and it being a diffusion model gives you superpowers like "the 4th word has to be pineapple" 🦸 Demo and weights 👇

00:00