I am sorry I did not understand all of it. But, would this allow running large MoE LLMs on a local network with experts spread out over multiple cheaper GPUs (or even CPUs)? This would perhaps be more useful than over the Internet, within offices for example.
Because everything stays local and latency is tiny, even modest always-on devices can contribute. A few Raspberry Pi 5s, old mini-PCs, or stronger IoT-style boards can each hold and run a handful of experts. The protocol doesn’t care if the peer is a big GPU or a small ARM box, as long as it can load the expert weights and do the matmul.
Pure busybox-class sensors are usually too limited in RAM and compute for current MoE experts, but the broader “every half-decent always-on box in the house joins the swarm” vision works well and keeps everything private inside your LAN.
Ho thanks for the comment.
Verification does not depend on temperature.
Expert execution is deterministic (pure matmul).
LUMABRI_VERIFY=N re-runs N% of the calls on a second replica and requires byte-identical output.
Temperature (and sampling) happens only on the chatter, after the experts return their activations.
So it can be any value (0, 0.7, 1.2…) without affecting the verification contract.
P2P inference sounds really nice and it would bring us back to the 2000s culture if not for the fact inference is already so cheap. Even so it is an insurance policy if the cloud providers or governments have ideas of further censoring and monitoring chats.
I am sorry I did not understand all of it. But, would this allow running large MoE LLMs on a local network with experts spread out over multiple cheaper GPUs (or even CPUs)? This would perhaps be more useful than over the Internet, within offices for example.
What if one wishes to use various busybox nodes within the house?
All the iot devices contributing to matmul but within a LAN?
Because everything stays local and latency is tiny, even modest always-on devices can contribute. A few Raspberry Pi 5s, old mini-PCs, or stronger IoT-style boards can each hold and run a handful of experts. The protocol doesn’t care if the peer is a big GPU or a small ARM box, as long as it can load the expert weights and do the matmul. Pure busybox-class sensors are usually too limited in RAM and compute for current MoE experts, but the broader “every half-decent always-on box in the house joins the swarm” vision works well and keeps everything private inside your LAN.
Cool idea. How do you handle temperature in the verification?
Ho thanks for the comment. Verification does not depend on temperature. Expert execution is deterministic (pure matmul). LUMABRI_VERIFY=N re-runs N% of the calls on a second replica and requires byte-identical output. Temperature (and sampling) happens only on the chatter, after the experts return their activations. So it can be any value (0, 0.7, 1.2…) without affecting the verification contract.
Wasn't a p2p ai model how skynet got started?
J/k, this looks cool :)
P2P inference sounds really nice and it would bring us back to the 2000s culture if not for the fact inference is already so cheap. Even so it is an insurance policy if the cloud providers or governments have ideas of further censoring and monitoring chats.
great work
Thanks for the support!