콘텐츠로 이동

FAQ

이 콘텐츠는 아직 번역되지 않았습니다.

No. CPU-only inference works on the Lite tier. GPUs are recommended for vision models and high-throughput workloads.

Yes. The runtime is fully air-gappable. License activation can be done via offline file.

ONNX is the primary format. Compiled TensorRT engines and sandboxed Python handlers are also supported.

All traffic on the device is mTLS. At-rest data is encrypted (LUKS) on supported hardware. RBAC is enforced for every API call.

Updates are signed container images. Roll forward and rollback are one-click in the dashboard.

Standard, Business, and 24/7 Critical. See Support.