The Serving Stack
Start hereCollectionsNewsletter
Sign in

latency

2 posts

SERVING IN PRODUCTION · 02QUIET · FIRST TOKEN, THEN A STEADY STREAMLOADED · LONGER WAIT, LONGER GAPSTHROUGHPUT UP, GOODPUT DOWN
serving-in-productionbenchmarkingobservability

TTFT, ITL, Goodput: Measuring What Users Feel

What TTFT, TPOT, ITL, end-to-end latency, and goodput each measure, how the tools compute them, and why peak throughput is the wrong target.

by The Serving Stack
SERVING IN PRODUCTION · 03SAME BENCHMARK,THREE RUNSMEDIAN TTFT 819 · 1,132 · 894 MS
serving-in-productionbenchmarkingvllm

Benchmark an Inference Server Without Lying to Yourself

Common load-test mistakes made on purpose next to the correct run, on one vLLM server, so each rule comes with how far it moves the numbers.

by The Serving Stack

Inference Notes

Once a week: what changed in serving AI models, and what it means if you build, run or pay for them, in about five minutes.

The Serving Stack

Inference Engineering, In Depth

Navigate

HomeStart hereCollectionsNewsletterAll articles

Collections

Inference EnginesHow an LLM Request Becomes TokensLLMs, ExplainedThe GPU for Inference EngineersQuantization in PracticeServing in Production

Links

RSS Feed

Legal

Privacy PolicyTerms of ServiceCookie Policy
© 2026 The Serving Stack. All rights reserved.