CONTROLConsumer & creative
TypeGPU + ruNNtime + Jev
Konrad Reczko@reczko_konrad
0:35This project combines ruNNtime for efficient local inference and TypeGPU for direct GPU resource sharing between inference and rendering, with Jev acting as a semantic processing layer in the pipeline.
TakeThat’s 3 separate NN inferences plus rendering, all happening in realtime Since we control the pipeline, Jev can just sit in the middle and add the semantic bit. camera + mic → Moonshine + YOLO26 + DepthART → Jev → lights, shadows and bloom
TypeGPU + ruNNtime + Jev @typesafeai is a very fun combo :D
ruNNtime gives me efficient local inference, TypeGPU lets inference and rendering share GPU resources directly with zero copy. That’s 3 separate NN inferences plus rendering, all happening in realtime
Since we control the pipeline, Jev can just sit in the middle and add the semantic bit.
camera + mic → Moonshine + YOLO26 + DepthART → Jev → lights, shadows and bloom