quiz bu lëkkale ak tegtal · Diggante Niveau

Deployée bu baxa-wert ngir quiz model ML

Xam dagg trafik bi ak dellu ginaaw ci génne yu baxa-wert, boole ci kàttan, deggoo schema ak àppu dellu ginaaw ci yoon wi.

Laaj 1 de 8

naka lañuy joxe environmaa bu baxa ak bu wert ci diiru génne gi?

Xoolaatal laaj bu nekk8 laaj

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

  1. naka lañuy joxe environmaa bu baxa ak bu wert ci diiru génne gi?
    • One serves current traffic while the other stages a candidate release
    • They store separate training and test labels
    • They run different model classes permanently
    • They split the GPU into two hardware drivers
  2. Lan mooy tax ñu mëna delloosi yoon wi gaaw ginaaw dagg bu baaxul?
    • The new model is retrained during every request
    • The previous environment remains available and healthy
    • The database schema is deleted
    • The old artifact was overwritten
  3. Lan moo tax ñuy waajal kàttan ngir baxa ak wert benn yoon?
    • The model runs on both environments after cleanup forever
    • Traffic is always doubled by the router
    • Both production-like environments may need resources during rollout
    • Blue-green requires two datasets
  4. Lan moo waral coppite yi ci base de done yi wara wéy di méngoo ak ñaari version yi ci diiru cutover?
    • Green must rewrite blue's weights
    • The router changes database columns automatically
    • ML models do not read data schemas
    • A rollback may return traffic to the older application or model
  5. Luy trafik lëndëm?
    • An automatic full production switch
    • Candidate predictions for comparison without serving them to users
    • A guarantee of zero latency
    • A replacement for model evaluation data
  6. What does routing rollback not necessarily undo?
    • The router's traffic target
    • Which environment receives future requests
    • External side effects or writes already made
    • The old environment's availability
  7. How does a canary relate to the basic blue-green cutover?
    • It only validates container image signatures
    • It is another name for two environments with no traffic shift
    • It eliminates the need for a green environment
    • It can expose a small traffic fraction before the full switch
  8. Why warm a large model in the green environment before switching?
    • It can reduce initialization delay and accelerator allocation surprises
    • It guarantees output quality
    • It eliminates the old environment's costs
    • It validates every subgroup metric