Inference when low latency and cost are critical
Turing RK1 Compute Module
Reliable, scalable computer
for the edge & AI apps
Turing Pi is a compact computer that hosts both regular applications and machine learning models for continuous inference. It unites compute modules into a cluster on a mini ITX motherboard for better performance and availability. 24/7, fanless and quiet with less than 80 W power consumption
Use Cases
Edge AI
Self-hosted
Development
As easy as
We combined practices from building server products: built-in BMC with CLI for remote bootstrapping from scratch to Kubernetes and Machine Learning stacks, support for compute modules from different vendors, including Nvidia
$ tpictl login
$ tpictl info
$ tpictl get nodes
$ tpictl flash node 1 -f ./ubuntu.img
$ tpictl reboot node 1
$ tpictl serial node 1
$ tpictl drain node 2
$ tpictl poweroff node 2
Spotted on
