Show HN: Lumabri – Run Moe Models on a P2P Swarm with Colibri

Discussion (8 Comments)Read Original on HackerNews

brainless•22 minutes ago

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.

s2l•20 minutes ago

What if one wishes to use various busybox nodes within the house?

All the iot devices contributing to matmul but within a LAN?

snovv_crash•about 1 hour ago

Cool idea. How do you handle temperature in the verification?

vforno•27 minutes ago

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.

Scaled•about 1 hour ago

Wasn't a p2p ai model how skynet got started?

J/k, this looks cool :)

ptsneves•about 2 hours ago

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.

RIshabh235•about 3 hours ago

great work

vforno•about 2 hours ago

Thanks for the support!

Show HN: Lumabri – Run Moe Models on a P2P Swarm with Colibri

⚡ Community Insights

Discussion (8 Comments)Read Original on HackerNews