05When is serverless the wrong choice? Talk me through cold starts and what they actually cost.▼mediumNewAmazonMicrosoftAtlassian2 repliesunlockedMost candidates can sell serverless. The question asks you to argue against it, which needs a real understanding of the execution model rather than the marketing.Open full answer →
16Your inference replica takes nine minutes from pod scheduled to first token served. Where does the time go and what do you fix?▼hardNewNVIDIADatabricksMicrosoft2 replies○ sign inSeparate scheduling delay from image pull, artifact transfer, GPU loading and warm-up. The autoscaler needs the full request-to-ready time.Open full answer →
23Finance wants your GPU inference service to scale to zero overnight. What do you tell them?▼hardNewDatabricksMicrosoftSnowflake2 replies◆ premiumScale to zero is correct for some workloads and an outage generator for others, and the deciding number is what the first request after idle experiences. Cold start turns an availability promise into a queue.Open full answer →
