• frongt@lemmy.zip
    link
    fedilink
    English
    arrow-up
    6
    ·
    1 day ago

    Yes, that’s basically what the article is about. They run the LLM across both GPUs.

    But that’s a feature of llama.cpp. SLI doesn’t really exist any more, and NVlink requires a specific setup, which the 4080 is not part of (the 3090 was the last consumer one, apparently). So you couldn’t pool the VRAM.