正在加载视频...
视频加载失败
Diffusion language models are SO FAST!! A new startup, Inception Labs, has released Mercury Coder, "the first commercial-scale diffusion large language model" It's 5-10x faster than current gen LLMs, providing high-quality responses at low costs. And you can try it now!
11 条评论

The performance is similar to small frontier models while achieving a throughput of ~1000 tokens/sec... on H100s! Reaching this level of throughput for autoregressive LLMs typically requires specialized chips.

It's currently tied for second place on Copilot Arena!

.@InceptionAILabs is a new company that is founded by some of the leading researchers in diffusion language models (@StefanoErmon, @adityagrover_, @volokuleshov)

You can try out Mercury Coder right now, over here:

Expand the possibilities of your metabolic research. Resipher tracks real-time cellular oxygen consumption in standard 96-well plates, delivering continuous real-time data directly from your incubator. Request a free virtual demo or quote today >>

Speed is cool! It did the '// This part is left as an exercise for the reader' thing on my first test though hahaha

Reporting as spam

🤣🤣🤣

Has it helped with any of the limitations of current autoregressive models? Like hallucinations; would be super exciting then.

open source?

@EastlondonDev i think you're right 3 months
