Show HN: Disaggregating GPU compute from CPU in ML job execution to scale GPUs

1 points by medicis123 8 months ago · 0 comments · 1 min read

WoolyAI disaggregates GPU compute from CPU and routes GPU operations from ML jobs running on CPU-only infra into a shared heterogeneous GPU pool(Nvidia+AMD), where a GPU hypervisor packs and schedules multiple jobs per GPU for maximum utilization.

Trial is now to triple your GPU Utilization in ML Development.

No comments yet.