Overview
AI Profiling — CPU, GPU, memory, token consumption, and per-step timing.
This page is part of the Documentation portal. The portal covers the conceptual heart of neuronscope. each chapter explains ai observability, ai evaluation, ai profiling, explainability, workflow intelligence, optimization, and governance.
When to use it
Reach for profiling when the problem in front of you matches its scope: cpu, gpu, memory, token consumption, and per-step timing.
- You need a canonical answer that survives environment changes.
- You want the behavior documented under a stability contract.
- You are cross-referencing this material from another portal.
How it fits
Each portal in NeuronScope owns one axis of the library. Documentation owns concepts, semantics, and contracts for every platform capability. Sibling pages in the sidebar cover the adjacent surface area — start there if this page does not answer your question directly.
Sibling pages in Docs
Next steps
- Return to the Documentation overview for the full page grid.
- Related portal: API Reference
- Related portal: Architecture
- Related portal: Cookbook