Roofline

TPOT is high, so the team plans to upgrade A100 to a faster compute GPU, critique

Find the wrong move in 'decode is slow, so let's switch to a smaller-FLOP model'

The roofline model in plain language, without the chart, what is it saying?

What does arithmetic intensity actually measure and what does AI near 1 imply?

Apply the roofline model to LLM inference and identify where decode and prefill sit on it.

On the roofline, which intervention moves an LLM decode workload most directly toward higher peak throughput?

Why does prefill saturate compute while decode is bottlenecked on memory bandwidth?

Why is HBM bandwidth the binding constraint for LLM decode and how do you reason about the 'memory wall'?

An engineer says 'FP8 KV cache just halves memory, no other benefit.' Which response is most correct?

Why is 'reduce FLOPs to speed up decode' the most common beginner misconception in LLM serving?

Predict the critical batch size where decode crosses from memory-bound to compute-bound on H100

As batch size grows, where does throughput stop increasing and per-request latency start exploding?

Predict the throughput and per-request latency behaviour as batch size grows past saturation

Spot the errors in this 'batching is universal' claim

Why does batching help LLM decode disproportionately more than batching helps CNN inference?

Predict the arithmetic intensity of decode at varying batch sizes