Apple researchers pool idle Mac GPUs into a shared inference cloud
Why it matters
Companies with fleets of Macs get a research route to running AI workloads on idle hardware instead of renting GPUs.
What happened
Apple researchers describe Minions, a system that pools idle GPUs on Apple Silicon Macs into a distributed virtual for running machine learning . It targets the cost, limited elasticity and queue times of centralized GPU infrastructure.
Tap an underlined word to see what it means.
The context No earlier Seventy story on this in the last 30 days.
Read the original at Apple Machine Learning Research
Something wrong in this story? Report a mistake. We check it against the source within 24 hours.
Share with your take
Start from our line and make it yours. It stays on your device until you post it.
Ask about this story
Answered only from this story, with the line it came from.