← Back to case library
Case / 2100646448324833512기타
Case media / 1MP4 ↗
Localized reading
TypeGPU + ruNNtime + Jev @typesafeai는 매우 재미있는 콤보입니다. :D runNNtime은 효율적인 로컬 추론을 제공하고, TypeGPU는 추론과 렌더링이 복사 없이 GPU 리소스를 직접 공유할 수 있게 해줍니다. 3개의 별도 NN이 있습니다.
Original post / EN
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
- views
- 7.1만
- likes
- 662
- saves
- 489
- reposts
- 59
출처
This independent archive preserves a public post with attribution. Text, media, account details and trademarks belong to their respective owners.
