Your product forecasts 12,800 output tokens per second at peak. Size the fleet.

Six steps forward from traffic, never backward from an available GPU count. The one input that has to be measured rather than derived, the headroom that is not optional, and the utilization term that moves cost per token more than any tuning flag.

Updated Sep 2026 · Grounded in real AI infrastructure interview loops and written to a senior-engineer editorial bar, with every number worked and every diagram hand-built.

more free answers with an account · no card

The concepts behind this question

Ranked by how closely each one overlaps this question's topic, so the first card is the thing to read if the answer above moved too fast.

Foundational

🧮 Open Weights & Serving Engines

Capacity Planning for Open-Weights FleetsPlanning a fleet for a sparse open-weights model works differently from planning one for a dense model, because memory follows total parameters and throughput follows active parameters, and those now differ by more than twenty times. The sizing goes in one direction only: from a traffic forecast to tokens per second, to replicas at a measured operating point, to GPUs, to racks and kilowatts. Doing it in the other direction, from an available GPU count, produces a fleet that fits the hardware rather than the demand.

Foundational

🧭 Ownership & Judgment

Talking About Cost and Capacity with LeadershipInfrastructure engineers are asked to justify large numbers to people who do not share their vocabulary, and the conversations go wrong in predictable ways: a technical objection with no alternative, a forecast with no assumptions, or a cost quoted in a unit the listener cannot act on. What works is a small number of costed options, a stated recommendation, the decision needed by a date, and every figure expressed in whatever the listener actually controls.

Foundational

🧮 Open Weights & Serving Engines

Reading config.json to Size a Model You Have Never RunEvery Hugging Face model ships a config.json, and it contains enough to compute the weight footprint, the KV cache per token, the parallel degrees that divide cleanly and the minimum GPU count, before downloading a byte. Doing that derivation is a standard whiteboard exercise in serving interviews because it is exactly what an engineer does on the morning a new model lands, and the fields that matter are the same across every recent architecture.

Advanced

🧮 Napkin Math & Capacity🔒 Premium

Capacity Planning and UtilizationCapacity planning for GPUs is deciding how many to have next quarter given that they cost money whether busy or not, that demand arrives in bursts, and that a queue near saturation produces waits that grow without bound. This page works the planning arithmetic for a serving fleet (peak demand, headroom, the p99 penalty of running hot) and a training platform (job mix, queue wait, the value of a shared pool), and gives the queueing intuition that makes 70% look full. The number that decides everything is utilization, and it has a ceiling set by latency, not by hardware.

Explore the full curriculum →

UP NEXT ON YOUR JOURNEY

Next in this trackIs speculative decoding worth enabling on a trillion-parameter mixture-of-experts model?Next in this trackYour deployment is limited by KV cache rather than by compute. What are the options?Next in this trackYour p99 time to first token is four times p50. Find out why.

FEDITOR'S NOTE

Scored on sizing forward from the forecast, on per-replica throughput at the SLO being the measured input, and on utilization dominating cost per token.

DISCUSSION · 0

No comments yet — be the first to share your approach.