News for hackers. Stuff that matters.

A comment on Mercury Coder: frontier diffusion LLM generating 1000+ tok/sec on commodity GPUs. Parent comment

Re:Mercury Coder: frontier diffusion LLM generating 1000+ to... by Reubend on Wednesday February 26, 2025 @06:05PM (#43189306)
Super cool, and I'd love to play around with this if they release an open source version.

Without a full paper, it's a bit hard to understand the full details. Does this essentially replace nucleus sampling with diffusion, or does it change the "core" transformer architecture in a major way?

[ Parent | on HN ]
Re:Mercury Coder: frontier diffusion LLM generating 1000+ to... by volodia on Wednesday February 26, 2025 @06:55PM (#43189713)
Yes, we plan to be releasing a tech report soon. We are not open sourcing the models at launch time, but we have a roadmap of future releases in which we hope to make some of our models accessible to the research community.
[ Parent | on HN ]