Mid-level interview question
Server logs show a TTFT of 80 ms, yet users of your reasoning assistant say it takes seconds to start answering. Explain the gap.
Model answer
TTFT counts the first generated token; the user waits for the first visible one, after every hidden plan or reasoning token, plus any tool calls. Some teams call that time to publish. In our CPU stream with the first 48 tokens hidden, the first visible token came at 504.2 ms instead of 67.5 ms. Measure what the user sees, alongside TTFT.
Practise the rest
17 Latency & throughput questions, 492 in all, each with a model answer. Free.
More Latency & throughput interview questions
- A chat reply streams in token by token. What two waits does the user feel, and which one does streaming make matter most?
- How do you get TTFT, inter-token latency, TPOT and total latency from one streamed reply?
- Why report p50 and p99 latency rather than the mean?
- You time a GPU request by reading the clock right after calling the model and get 0.3 ms per token. What went wrong, and what else can silently skew a timing?
- Your team wants to raise the batch size to cut serving cost. What happens to users, and which number would you use to decide?
- Explain how a server like vLLM runs a decoder-only model efficiently.