profiling

A confirmed Anthropic live-coding question that looks exotic and reduces to one operation: diff consecutive call stacks against their common prefix. The recursion edge case is where strong candidates separate from finished-but-wrong ones.

The roofline model in one ratio: FLOPs per byte against the hardware's ridge point. Get the H100 arithmetic right and you can classify any kernel, including why LLM decode will never be compute-bound at batch 1.