Seldon Core ak Graafik

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Lan mooy màndarga biy wuutale Seldon Core ak serwër bu am benn model?
   • Graafiku inferensi buy boole ay komponent yu bari
   • Taggat model buñ tabax ci biir
   • Dawalkatu GPU buñ moomeel
   • Etiketu done otomatik
2. Ban cër ci graf Seldon mooy dogal ci ban node xale lañuy yónnee laaj bi, ngir mëna def test A/B?
   • Transformatër
   • Routeur
   • Kombinatër
   • Modèle
3. Ban xeetu komponent mooy boole ay génn ci model yu bari ngir boole?
   • Routeur
   • Transformatër
   • Kombinatër
   • tàmbalikat
4. Ban xeetu jëmmu graf la graf inference Seldon di forme?
   • mbaal siklik
   • Limu plat
   • Garab binër kese
   • Graaf asiklik buñ jubal (DAG)
5. Ci Seldon Core v2, ban serwër ak protokol mooy tax model yu bari di liggéey ci graphe bi?
   • MLServer ak protokol ubbite
   • TensorFlow di liggéey ak gRPC kese
   • Nginx ak REST
   • Lumière et parquet
6. In the Seldon Core 1 Router documentation, what can shift traffic toward better-performing models over time?
   • Nightly retraining only
   • A multi-armed bandit using live reward signals
   • Increasing the pod CPU limit
   • Caching every response
7. Which Seldon graph component can preprocess a request or postprocess a model response?
   • Kombinatër
   • Routeur
   • Transformatër
   • Explainer
8. Which description of Seldon Core 2 observability is accurate?
   • Metrics, tracing and payload logging are all automatically enabled for every REST/gRPC prediction
   • It provides only GPU metrics and no tracing
   • Payload logging always stores every model request in a local file
   • Metrics are exposed; tracing requires configuration, and payload logging is limited to configured Kafka-backed pipeline paths