thickertoofan@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 1 month agoSpatialLM, a 1B model capable of spatial identification, using 3d point cloud data. The video demo is amazing.manycore-research.github.ioexternal-linkmessage-square5linkfedilinkarrow-up117arrow-down10
arrow-up117arrow-down1external-linkSpatialLM, a 1B model capable of spatial identification, using 3d point cloud data. The video demo is amazing.manycore-research.github.iothickertoofan@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 1 month agomessage-square5linkfedilink
minus-squareKarkitoo@lemmy.mllinkfedilinkEnglisharrow-up3·1 month agoLooks impressive and it’s truly open-source. However, I see it requires CUDA. Could it run anyway: Without this? With AMD hardware? On mobile (as the model is only 1B) ?
minus-squarethickertoofan@lemm.eeOPlinkfedilinkEnglisharrow-up1·1 month agoI think the bigger bottleneck is SLAM, running that is intensive, it wont directly run on video, and SLAM is tough i guess, reading the repo doesn’t give any clues of it being able to run on CPU inference.
Looks impressive and it’s truly open-source.
However, I see it requires CUDA. Could it run anyway:
I think the bigger bottleneck is SLAM, running that is intensive, it wont directly run on video, and SLAM is tough i guess, reading the repo doesn’t give any clues of it being able to run on CPU inference.