Your inference server OOMs when requests arrive with long prompts. How do you handle variable-length memory?
A serving box steady on short prompts falls over the instant a 30k-token request arrives, because KV-cache memory scales with sequence length times batch. Here is how to bound it without crashing.
Updated Sep 2026 · Grounded in real GenAI, LLM, and AI/ML engineering interview loops and written to a senior-engineer editorial bar.
A serving box steady on short prompts falls over the instant a 30k-token request arrives, because KV-cache memory scales with sequence length times batch. Here is how to bound it without crashing.
Lead with where the obvious approach breaks, because that is the judgment they are screening for — most candidates jump straight to the happy path and lose the room.
Then walk the failure back through the pipeline in order, naming the one metric the customer's exec sponsor actually cares about before you propose the fix.
