decode

1 article

LLM Inference Roofline Model: FLOPS vs HBM Worksheet

A 2026 buyer worksheet for LLM inference roofline analysis: calculate arithmetic intensity, check precision-specific GPU peaks, separate prefill from decode, and request evidence for an SLO-qualified pilot.

October 31, 2026• 23 min read
llm inference roofline modelllm inferencearithmetic intensity