• boonhet@sopuli.xyz
    link
    fedilink
    English
    arrow-up
    2
    ·
    3 hours ago

    It’s KINDA being done in the ways we run MoE models. Strata makes more efficient use of limited VRAM if you have a decent amount of RAM, but you don’t even need to keep the entire model in RAM with it, it can keep the least frequently used experts on disk instead (said disk being an NVMe SSD hopefully, otherwise if you hit those experts, good luck)