its a great day to build decentralized inference

reasoning has never been so accessible

Announcing our $15m raise — led by Founders Fund. To build our peer to peer compute and intelligence protocol. With participation from Menlo Ventures and angels like Andrej Karpathy clem 🤗 Tri Dao Dylan Patel Balaji Emad and many others.

Today we’re launching INTELLECT-2: The first decentralized 32B-parameter RL training run open to join for anyone with compute — fully permissionless. Scaling towards frontier reasoning across coding, math and science.

wrote a little something on our learnings from decentralizing inference and open-sourced 3 research codebases. tl;dr optimizing inference under decentralized constraints is worthwhile, non-trivial, and far from solved. excited to be building this with the team! more soon, when we

Very excited to soon release SYNTHETIC-2, partially powered by consumer grade GPUs. Very confident that what we’ve planned for this dataset will be incredibly useful for the open source community

We wrote an extensive blog post on large-scale pipelined inference and released a VLLM integration to connect any machines over the internet to serve a model. Will be the foundation of our next synthetic-2 run (and later allow consumer GPU to join rl run)

legend

we are just getting started

Releasing INTELLECT-2: We’re open-sourcing the first 32B parameter model trained via globally distributed reinforcement learning: • Detailed Technical Report • INTELLECT-2 model checkpoint primeintellect.ai/blog/intellect…

insane to see mike64_t and Mario Sieg pull this off over the last few months

recommend prime-rl to your friends

i can’t wait to launch synthetic-2 Prime Intellect

with synthetic-2 we scaled heterogeneity across not 1, not 2, but 3 axes in a single shot. we run on a variety of models, tasks and hardware, all while allowing completely permissionless compute contributions. on the surface it might just seem like a dataset release, but so much