quiz bu lëkkale ak tegtal · Diggante Niveau

KServe ak xeetu liggéey ci Kubernetes

Saytu InferenceService bu KServe, modelu sargal artefakt, eskalaasioŋ otomatik ci diiru daw, komponent yiy liggéey ak protokolu wax luy waaja am buñ yamale.

Yooni njiit yu jëm ciKserve ak xeetu liggéey ci Kubernetes
Laaj 1 de 8

Lan moo nekkoon tuuru KServe balaa muy nekk projet bu nekk boppam?

Xoolaatal laaj bu nekk8 laaj

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

  1. Lan moo nekkoon tuuru KServe balaa muy nekk projet bu nekk boppam?
    • KFSërwiŋ
    • KubeML
    • ModelMesh
    • Modèle Knative
  2. Lan mooy jumtukaayu Kubernetes bi njëkk bi nga tànn ngir dugal ab model ak KServe?
    • Modèle de déploiement
    • Serwiisu Inferensi
    • Pod
    • tablo sargal
  3. Ban mënin mooy tax model KServe yi duñu def benn ordinatër ba keroog laaj bi yegsi?
    • Canary
    • Xaajale
    • Eskale-ba-nul
    • Inférens ci lots
  4. Ban projet mooy joxe autoscaling bu lalu ci laaj bu KServe?
    • Prometée
    • Casco
    • Argo
    • Knatif
  5. naka la ko KServe di def ba mëna am ay model ci pod biy tàmbali?
    • Jaaraleko ci ab tàmbalikatu dencukaay buy génne ci dencukaay mbir
    • Ni ñuy lakkee xeetu lakk yi ci nataalu resinto bi kese
    • Soo yónnee fichier model bi ci imeel
    • jaaraleko ci benn kopi kubectl
  6. Ban standard la KServe di jëfandikoo ngir kiliyaan yi mëna woo model yu wuute ci anam wu wuute?
    • Federaasioŋ GraphQL
    • Protocolu inférence bu ubbeeku bi
    • SAABU
    • JDBC
  7. In KServe’s InferenceService pipeline, which component can apply pre- or post-processing around the predictor?
    • The storage initializer
    • The Knative autoscaler
    • Transformatër bi
    • The Kubernetes scheduler
  8. What is a typical trade-off of scaling a model deployment down to zero replicas?
    • The model becomes permanently unavailable
    • Every request avoids model loading
    • The Kubernetes API is replaced
    • Idle compute is reduced, but the next request may incur a cold-start delay