News for hackers. Stuff that matters.
Re:Mesh LLM: distributed AI computing on iroh by SwellJoe on Sunday July 12, 2026 @05:20AM (#48879640)
Ah, that's interesting. I though there was more data crossing the network. So, why does a DGX Spark come with super fast network if 10Gbps ethernet would be sufficient for splitting a model? I never bought a second Strix Halo on the assumption that the pipe between them would be a limiting factor to using larger models, so obviously there's something I don't understand.
Re:Mesh LLM: distributed AI computing on iroh by stymaar on Sunday July 12, 2026 @07:35AM (#48880304)
The amount of data is only low for inference, not for training, and AFAIK DGX spark is supposed to be a researcher's machine that can do small-scale training.