Maswali ya Grafu za Seldon Core na Inference

Majibu na maelezo huonekana unapojibu maswali.

1. Ni kipengele gani kinachofafanua kinachotofautisha Seldon Core kutoka kwa seva ya mfano mmoja?
   • Grafu za uelekezaji zinazofunga vipengele vingi
   • Mafunzo ya mfano yaliyojengwa
   • Kiendeshaji cha GPU inayomilikiwa
   • Kuweka data kiotomatiki
2. Ni sehemu gani ya grafu ya Seldon inayoamua ni nodi gani ya mtoto kutuma ombi, kuwezesha majaribio ya A/B?
   • Kibadilishaji
   • Kipanga njia
   • Mchanganyiko
   • Mfano
3. Ni aina gani ya sehemu inayojumlisha matokeo kutoka kwa miundo mingi ya kukusanyika?
   • Kipanga njia
   • Kibadilishaji
   • Mchanganyiko
   • Mwanzilishi
4. Je! ni aina gani ya muundo wa grafu ambayo grafu ya uelekezaji ya Seldon inaunda?
   • Mesh ya mzunguko
   • Orodha ya gorofa
   • Mti wa binary pekee
   • Grafu ya acyclic iliyoelekezwa (DAG)
5. Katika Seldon Core v2, ni seva gani na itifaki gani huwezesha huduma za modeli nyingi kwenye grafu?
   • MLServer na Itifaki ya Uelekezaji Wazi
   • TensorFlow Serving na gRPC-pekee
   • Nginx na REST
   • Spark na 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?
   • Mchanganyiko
   • Kipanga njia
   • Kibadilishaji
   • 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